Entries for 2026
1 to 5 agents
As a software developer, my daily workflow has changed completely over the last 1.5 years.
@onusoz · 2026-03-08
To set up Claude Code easily,
1. Create a Telegram topic, make sure your agent can receive messages there
2. Copy and paste the text below, into the topic
"""
bind this topic to claude code in openclaw config with acp, for telegram (agent id: claude)
then restart openclaw
docs are at: docs dot openclaw dot ai /tools/acp-agents
make sure to read the docs first, and that the config is valid before you restart
"""
h...
Using coding agents in Telegram and Discord via ACP
Use Claude Code, Codex, and other coding agents directly in Telegram topics and Discord channels, through Agent Client Protocol (ACP), in the new release of OpenClaw
Previously this was limited to temporary Discord threads, but now you can bind them to top level Discord channels and Telegram topics in a persistent way!
This way, you can use Claude Code freely in OpenClaw without ever worrying about getting your ...
Telegram/Discord is my IDE
OpenClaw got very popular very fast. What makes it so special, that Manus does not have for example?
@onusoz · 2026-03-07
and for the love of god
- do not give openclaw access to your main email
- your credit cards
- your main phone
- your social security number
- what you did last summer
if you are not ready to face the consequences
instead,
- create accounts for your agent
- only give it read access to stuff that will be ok if it leaks
- give write access in a way that can be undone, like has to open PRs and cannot force push ma...
AI security, the lethal trifecta, and Linus's Law
openclaw is not secure
claude code is not secure
codex is not secure
any llm based tool:
1. that has access to your private data,
2. can read content from the internet
3. and can send data out
is not secure. it’s called the lethal trifecta (credits to @simonw)
it is up to you to set it up securely, or if you can’t understand the basics of security, pay a professional to do it for you
on the other hand, open...
@onusoz · 2026-03-07
Let me translate. “This is your last opportunity before thousand years of serfdom”
@onusoz · 2026-03-05
Apparently the magic incantation to prevent this is "cutover". Credits to obviyus, fellow maintainer
@onusoz · 2026-03-05
Should be called gaslighting detector, "it's your raising expectations bro"
No it's not... Give the @themarginguy a follow
Also, codex degradations are not a hallucination either, if you are to believe this!
@onusoz · 2026-03-04
Who is building an OpenClaw ready linux distro? A ClawOS?
GitHub needs first-class support for working with agents
Secure agentic dev workflow 101
- Create an isolated box from scratch, your old laptop, vm in the cloud, all the same
- Set up openclaw, install your preferred coding agents
- Create a github account or github app for your agent
- Create branch protection rule on your gh repo "protect main": block force pushes and deletions, require PR and min 1 review to merge
- Add only your own user in the bypass list for this...
@onusoz · 2026-03-03
If I were in OpenAI and Anthropic's shoes, I would also make dashboards where I can track number of swearwords used per-user and overall negative sentiment in sessions
Must be so cool making decisions at the top level with all those dashboards
Intelligence wants to be free
It must be such a weird feeling for big labs when the service they are selling is being used to commoditize itself
I am using codex in openclaw to develop openclaw, through ACP, Agent Client Protocol. ACP is the standardization layer that makes it extremely easy to swap one harness for another. The labs can't do anything about this, because we are wrapping the entire harness and basically provide a different UI f...
@onusoz · 2026-03-02
I was so confused... as if accidentally using claude code weren't enough, acp started working... turns out hitting quota is rendered like this. need to improve error messages coming form acp subagents
@onusoz · 2026-03-02
accidentally told my clanker to set up a claude code session instead of codex session, god knows what it did...
I should probably put visual indicators for harnesses in subagent threads. does anyone have good and compact ascii art for claude code, codex, gemini, etc?
@onusoz · 2026-03-02
if something could track my local branches in all my repos, and switch to main when corresponding PRs get merged, that would be extremely useful
did someone build this already? if not I will
@onusoz · 2026-03-02
Another one, OpenClaw users only: If you use coding agents to build stuff, which one do you use?
@onusoz · 2026-03-02
OpenClaw users: Which messaging app do you use OpenClaw through?
@onusoz · 2026-03-02
Check xTap out, it's very cool!
@onusoz · 2026-03-02
This is how we hire at @TextCortex as well
@onusoz · 2026-03-02
Claude Code/Codex in Discord threads with ACP should be better now
The first release was a very rough first version. 2026.3.1 brings settings to control noisy output and other improvements
It now hides tool call related ACP notifications, coalesces text messages, and delivers messages at turn end by default. Without this, you were getting thousands of Discord messages just in just a few turns
You can now stop t...
@onusoz · 2026-03-01
Will get better, promise
Use plans to survive agent context compaction
pro-tip on how to keep your agent on track and make sure it follows PLANS even after multiple compactions. I don't know if this is common knowledge
if the thing you are trying to make it do will take more than 1-2 steps, always make it create a plan. an implementation plan, refactor plan, bugfix plan, debugging plan, etc.
have a conversation with the agent. crystallize the issue or feature. talk to it until ther...
@onusoz · 2026-03-01
testing codex in discord thread with another CLI I've built for wikidata (gh:osolmaz/wd-cli)
it's surprising how well this works. the query was "use wd-cli to get the list of professors at middle east technical university from 1970 to 1980"
some names I recognize, and some others are surprising, like a japanese math professor who naturalized and got a turkish name:)
@onusoz · 2026-03-01
OpenClaw is already higher than Claude Code and Codex on Google Trends, this was unexpected for me
Building a static X to blog publishing flow
my blog now semi-automatically detects tweets that look like blog posts and automatically features them alongside my native jekyll blog posts. all statically generated!
I am loving this setup, because it works without a backend, and can probably scale without ever needing one
how it works:
- @kubmi's xTap scrapes all posts that I see. these include mine
- a script periodically takes my tweets and the ones I quot...
Inference scaling can reduce coding model quality
"this is the worst AI will ever be"
I'm sad, not because this is right, but because it is wrong
OpenAI's frontier coding model gpt-5.3-codex-xhigh feels a lot worse compared to before. It is sloppy and lazy, though it's UX got better with messages
It feels like the gpt-5.2-codex-xhigh at the end of December was a lot more diligent and thorough, and did not make stupid mistakes like the one I posted before. migh...
Archiving my X posts in my own blog
I created a semi-automated setup for ingesting X posts into my blog, and it works pretty well! I own my posts on X now
Posts are scraped while I browse X using @kubmi's xTap and get automatically synced to my blog repo. Posts saved as jsonl are then converted to jekyll post pages according to my liking
I reproduced the full X UI/UX, minus stuff like like count. Now all my posts are backed up in my blog, and they...
Agentic Engineering needs rigor, not just intuition
Agentic Engineering is a newly emerging field, and we are the first practitioners of it. Currently there is a lot of experimentation going on, and there is a large aspect to it that is more ART then engineering
For example, @steipete says "you need to talk to the model" to get a feel. a lot of work around refining how an agent feels like, sounds like psychology. this part is crucial and should not be ignored, loo...
@onusoz · 2026-02-27
this is an insane deal @greptile, and probably an unsustainable one
depending on your team, getting a similar service in codex github review credits is in my head 3~5x more expensive
go get a greptile sub everyone while the free lunch lasts
@onusoz · 2026-02-27
who remembers ultrathink
https://t.co/ftCauqiKx6
@onusoz · 2026-02-27
oohh colors in codex v0.106
@onusoz · 2026-02-27
mfw codex tries to create a backward compatibility layer to a schema that it created 2 turns ago before compacting
there is no v2 bro what are you doing...
@onusoz · 2026-02-27
Note that this is currently in beta, but will ship in a couple of hours
@onusoz · 2026-02-27
Claude Code / Codex in Discord threads is shipped now!
To enable, copy and paste this to your agent:
```
Enable feature flags:
acp.enabled=true
acp.dispatch.enabled=true
channels.discord.threadBindings.spawnAcpSessions=true
Then restart. After restarting:
Start a codex (or claude code) discord thread using ACP, persistent session, just tell it to write a haiku on lobsters to initialize acpx for the first time...
@onusoz · 2026-02-26
an agent is an LLM in a loop with tool call
a claw is an agent in a messaging app
@onusoz · 2026-02-26
Update acpx to the latest version 0.1.13
npm i -g acpx@latest
There was a bug that caused an unnecessary hang on calls to acpx <harness> prompt, should be fixed now
@onusoz · 2026-02-26
GPL*
MIT licensing as the default for open source
MIT License on everything from now on. It doesn't make sense to use anything else, except for a few large projects that hyperscalers exploit and not give back
If you were making money from a niche app, open source it under MIT License
If you had an open source project with GPT, convert it into MIT
Extreme involution is about to hit open source. Code is virtually free now. If you want your projects and their br...
@onusoz · 2026-02-25
I spoke in absolute terms, I meant to say *feels*
@onusoz · 2026-02-25
This. Agent Experience first. Agent Ergonomics. we need to get used to these terms
@onusoz · 2026-02-25
OpenAI nerfed GPT 5.3 Codex xhigh. We independently reported the same thing at @TextCortex today
I'm looking forward to deploying open models and putting an end to this paranoia
@onusoz · 2026-02-25
"academics"
@onusoz · 2026-02-25
In the hall of OpenClaw GitHub repository, I brought my PR before Master @steipete
He read it once, then laid it aside
"You act," he said, "as if code were not cheap."
At these words, I was enlightened
I bowed
@onusoz · 2026-02-24
woah chatgpt web app now has steering, and much more different streaming behavior
huge upgrade behind the scenes, must have come up in the last few days
@onusoz · 2026-02-24
the lobster looks good on acpx
AI filmmaking quality beyond ragebait content
imagine if tarantino were 16 years old now and saw seedance 2.0
95% of videos i saw since the launch for absolute tasteless slop. they are going viral because of ragebait
but soon, serious imagineers will start entering the game, and they will learn to shape generation output exactly how they want
it's the best time to be young and full of imagination
@onusoz · 2026-02-23
The future is so bright @ladybirdbrowser
@onusoz · 2026-02-23
your margin is my opportunity
@onusoz · 2026-02-23
codex in discord achieved
@onusoz · 2026-02-23
acpx v0.1.7 is out
improvements to json mode and other functionality to make it possible to integrate acpx as a backend into other harnesses, like openclaw
@onusoz · 2026-02-23
POV: you became a plumber after all, just for agents
@onusoz · 2026-02-23
@grok what do you think should replace it? what happens to belief when the cost of creating software goes to zero?
Post-GPL philosophy for open source
another thought i'm having these days is that we need a new philosophy of free software (as in freedom), or an update to it
the most psychologically imprinting philosophy is stallmanism, and the philosophy of FSF. it is righteous and strict, and i believed it growing up
but GPL and money don't go well together. that's why most of the lasting open source projects today use MIT, Apache and the like. it turns out y...
@onusoz · 2026-02-22
@thekitze wanna add an open source discord clone to the list as well? 🥲
https://t.co/a4bAOcxCjV
@onusoz · 2026-02-22
one effect openclaw had on me is that I've bought a gpu home server, set it up with tailscale and now doing a lot of work through ssh and tmux like i did 10-15 years ago
im back on linux, considering buying an android phone again
it's time to dream big again and unshackle ourselves from proprietary software. it's time to build
@onusoz · 2026-02-22
I am asking once again
Who is building a self hostable discord clone that supports token streaming?
PLEASE I beg you I don’t want another side project 💀
@onusoz · 2026-02-21
In the new release OpenClaw, you can talk to subagents in Discord threads
Currently a beta feature so ask your agent to set
session.threadBindings.enabled=true
Next up:
- Telegram, slack, imsg threads
- Use ACP to talk to Codex, Claude Code and other harnesses on your machine
@onusoz · 2026-02-21
😎
@onusoz · 2026-02-21
openclaw might be the highest velocity codebase in the world, and soon, others will follow as well
conflict anxiety is real, it's like trying to shoot a moving target every time. I wonder if our existing tooling will ever solve this problem
feel like faster models might. but then the rate of conflict creation is also tied to that. might be unsolvable
@onusoz · 2026-02-21
Getting there
https://t.co/jqSNcH2PSy
@onusoz · 2026-02-20
Repo: https://t.co/rxXYVVrHHs
@onusoz · 2026-02-20
I am about kick Discord Driven Development up a notch today, stay tuned
@onusoz · 2026-02-20
Imagine not having to upload skills to 3-4 competing skill registries for each of your projects
Turns out we already have a skill registry: npm
skillflag lets you bundle skills right into your CLI's npm package, so that you can run
--skill install
github -> osolmaz/skillflag
@onusoz · 2026-02-20
Scoop, our open source home news intelligence platform can now translate foreign language into english for free, using on-device models
github -> janitrai/scoop
@onusoz · 2026-02-20
A picture is worth a thousand words, so acpx now has this cute banner
Also, updated skillflag tooling so that you (or better, your agent) can just call:
npx acpx@latest --skill install acpx
@onusoz · 2026-02-20
Farmable land if it were as cheap to manufacture as software
@onusoz · 2026-02-20
@kepano I would grow my own vegetables if I had equally cheap access to and ownership of land, alas I am disenfranchised
Prompting an agent is much easier compared to plowing a fields
Farming analogies break when it comes to software
https://t.co/CkldO8eWKc
@onusoz · 2026-02-20
acpx v0.1.5 is out
now it is much more feature complete in terms of ACP. your agent can send, queue and cancel messages to Claude Code, Codex, Pi, or ant other coding agent
npm install -g acpx@latest
@onusoz · 2026-02-19
If anyone is curious how to build this with open tooling, stay tuned
What I'm building at @TextCortex will give you a fully customizable hackable Kubernetes control plane to launch agents on your codebase
Family intelligence and privately owned heirloom AI
on another note, I do believe AI will play a huge part in families
growing up in late 90s, my dad taught me the importance of reading newspapers and being informed of the world. my nickname in middle school was "newspaper boy" for a long time because I read the newspaper in class on September 12, 2001. i was 10 years old
then I witnessed the enshittification of media and journalism in the following decades. toda...
AI psychosis, self-regulation, and sterile agent design
on ai psychosis
80% of people need to use ai agents in a very sterile and boring way in order not to go crazy
majority of the population does not have the skepticism muscle. they don't have theory of mind, and will subconsciously and emotionally associate with machines, while on the surface lying to themselves that they don't
especially those that grew up in the us under hardcore consumerism and adjacent cultur...
@onusoz · 2026-02-19
😩
@onusoz · 2026-02-18
I have improved acpx sane defaults
When your agent runs acpx codex in a different project, it starts a new session
If it tries to run it in a subfolder in your project, it still finds the session in your repo root
Also, starting a session needs an explicit `sessions new`, so that it doesn't accidentally litter your project with sessions
Tell your agent:
Run this and install acpx per instructions:
npx acpx@lat...
@onusoz · 2026-02-18
Your markdown files are executables now
Relatedly, your install instructions can be as well. Copy and paste markdown to your @openclaw to install acpx
@onusoz · 2026-02-18
So who is building actually good open source self hostable discord that supports token streaming now?
And who is building an open source version of codex desktop app?
@onusoz · 2026-02-18
and of course, I've used `acpx codex` to build acpx itself...
magical feeling when the tool builds itself
@onusoz · 2026-02-18
Oxidize everything!
@onusoz · 2026-02-18
I am a fan of @zeddotdev by this point, it’s currently my daily driver
It’s not perfect, but I feel it’s travelling on the right direction at a faster rate compared to other editors
@onusoz · 2026-02-18
ACP appreciation post
Agent Client Protocol by @zeddotdev is extremely underrated right now. We have bazillion different harnesses now, and only one company is working competently to standardize their interface 💪
@onusoz · 2026-02-18
Repo link: https://t.co/rxXYVVrHHs
@onusoz · 2026-02-18
You know how it's a pain to work with codex or claude code through @openclaw? Because it has to run it in the terminal and read the characters for a continuous session?
I have created a CLI for ACP so that your agent can use codex, claude code, opencode etc. much more directly
Your agent can now queue messages to codex like how you do it
Shoutout to @zeddotdev team for developing the amazing Agent Client Protoc...
@onusoz · 2026-02-17
@MarcTerns @steipete the PR intro is self-descriptive, but still don't wanna lose any context
@onusoz · 2026-02-16
Link to the post: https://t.co/C3Ac0jLFwh
@onusoz · 2026-02-16
I wrote a deeper blog post about how I built a coding agent 2 months before ChatGPT launched, on my blog
"When I made icortex,
- we were still 8 months away (May 2023) from the introduction of “tool calling” in the API, or as it was originally called, “function calling”.
- we were 2 years away (Sep 2024) from the introduction of OpenAI’s o1, the first reasoning model.
both of which were required to make current...
@onusoz · 2026-02-16
Who here remembers the OG Codex launch from 2021 😏
Also, Greg and Ilya in the same room 😭
@onusoz · 2026-02-16
❌We are the bottleneck
✅We are the conduit for ubiquitous intelligence
@onusoz · 2026-02-16
For those that are running codex/pi/etc. in PTY and had the sessions get sigkilled, I pushed a fix for that as well in this release
Lmk if you run into issues on Windows or Mac, and we can fix that quickly
@onusoz · 2026-02-15
I'm building a news intelligence platform to be used by my openclaw instance @dutifulbob, SCOOP
local first, using local embedding model (qwen 8b)
ran into the issue because bob was giving me a repeat of the same news every day. it needed a system in the background to deduplicate different news items into single stories
interface is simple, call `scoop ingest...` with the json for the news item. it gets automat...
@onusoz · 2026-02-15
Training all these models of different sizes, on changing datasets and running experiments have also revealed some challenges that I feel profs would never teach at a uni ML program
Like how to cleanly keep track of the gazillion runs
Yeah I can name them after layer dims and other stuff, but that's to me like trying to remember UUIDs
So I ended up choosing iso datestamp + petname, like 2026-02-15-flying-narwha...
@onusoz · 2026-02-15
I have a GPU now, so I can do ML experiments on @janitr_ai crypto/scam detection dataset
- I trained a tiny student BERT (transformer for the nonfamiliar), 3.6 MB ONNX model, still lightweight for a browser extension
- Still fully local on your device (no cloud inference)
- On frozen unseen holdout data (n=1,069), exact prediction accuracy improved from 77% -> 82%
- Scam detection improved: precision 91% -> 94%, ...
@onusoz · 2026-02-15
LFG!
@onusoz · 2026-02-15
waiting compilation and execution will soon be the bottleneck again. and we’ll write the entire stack from scratch in a matter of years, because we can
Andy and Bill’s law will change and we’ll see incredible performance gains with the same hardware we already have
like what @astral_sh is doing to python, but with everything that is slow and has accumulated cruft
We need a protocol for agent-to-app interaction
we need a protocol for agent <> app interaction
something that natively accounts for the abuse factor and let’s agents consume by paying. NOT crypto, NOT visa, something that’s agnostic of the accounting and payment system
and then all UIs will be purely for human clicking/tapping + instaban on the first proof of programmatic exploit
people will still make agents mimic humans, and every platform will have to in...
@onusoz · 2026-02-15
I am now training smol bert models on my gpu for @janitr_ai scam detection
it's funny how I have to discover everything from scratch. like the models don't even know how to lay out performance metrics in a nice way in the terminal for a human to view and decide during experiments
it would by default bombard me with numbers that do not make visual sense. I then created a skill with common sense:
- metrics always...
@onusoz · 2026-02-14
no other occupation has been catapulted from one end of the spectrum (autism) to the other (adhd) in such a short time
SaaS must adapt to agent consumption or get replaced
I've helped our sales team to build CLIs for some SaaS that we pay for on their side
We are letting our agents call the APIs sensibly and not abuse things
Calling a backend is a verifiable task. It takes a single prompt to codex to create a CLI for any API
We are early, but everybody will start doing this very soon. Incumbent SaaS will face a choice. Either:
(1) embrace agents and the new medium of consumption...
@onusoz · 2026-02-14
Be careful about giving your openclaw access to your x account from now on
@onusoz · 2026-02-13
The good thing about @levelsio and others flagging AI replies in public is that they are perfect annotations for the open @janitr_ai dataset
Just searching “blocked for ai reply” yields hundreds of samples for seed data
@onusoz · 2026-02-13
github added a new agents tab between pull requests and actions. single glance and i don't feel like giving it a try at all
@onusoz · 2026-02-13
*puts on schmidhuber hat*
well ackshuaally i created the first coding agent back in 2022, 2 months before chatgpt launched
jokes aside, it's super cool how I have come full circle. back in those days, we didn't have tool calling, reasoning, not even gpt 3.5
it was codex THE CODE COMPLETION MODEL and frikkin TEXT-DAVINCI-003
for some reason, I did not even dare to give codex bash access, lest it delete my home ...
@onusoz · 2026-02-13
you can order bubble tea in qwen in china?
@TextCortex when berlin döner in zenochat?
https://t.co/O4I950ltEO
@onusoz · 2026-02-13
it happens these days that I am telling an model to prompt another model. the reason is often the model I am using (opus) is a bad designer. not only it's not a bad designer, it is a bad reasoner and it doesn't understand from the context why it's made to ask another model
so I have to create a skill to prevent it from biasing the smarter model (codex) with its bad suggestions
I built a coding agent two months before ChatGPT existed
I built a coding agent back in 2022, 2 months before ChatGPT launched:
@onusoz · 2026-02-12
casually creates a local embedding service running qwen3-embedding-8b
@onusoz · 2026-02-12
"we're sitting on a beast and paying openai for embeddings like chumps"
@onusoz · 2026-02-12
don't buy mac mini. give your @openclaw a gpu
@onusoz · 2026-02-12
it's so interesting what identity an LLM decides to take on for itself
@onusoz · 2026-02-12
it's quite entertaining transferring one agent to another machine, agent gets confused as to where it lives
@onusoz · 2026-02-12
brb @dutifulbob's getting a new shell
@onusoz · 2026-02-11
Minor update with my unwanted tweet blocker @janitr_ai
- Training data grew from 2,915 -> 4,281 posts (+47%)
- Model is still tiny: 166KB
- On unseen test data, overall classification quality improved from 64.8% -> 76.5%
- Exact prediction accuracy improved from 55.6% -> 70.6%
- Crypto-topic detection recall improved from 19.6% -> 62.7%
And it still runs fully on your device!
@onusoz · 2026-02-10
I have sweared at codex 5.3 numerous times today
I shouldn't have to insult my agent "stop you **** **** just ***ng reply now" just to make it answer basic questions
cc @thsottiaux
@onusoz · 2026-02-10
on a brighter note, you can immediately tell a slop PR owing to the guerilla branding, so they should not stop doing it
@onusoz · 2026-02-10
seeing this evokes visceral disgust and nausea in me, coming from a coworker
i think anthropic f'd up bad with this one, inserting claude too visibly into commit messages. noob developers might be happily chirping away adding their slop, but right now many senior developers are trained to hate on claude and slopus, through having to review slop PRs from their coworkers or open source contributors
I love opus on ...
@onusoz · 2026-02-09
ask your openclaw to be a minion and it turns into such a cute doofus
i feel like a woman in her 50s now
@onusoz · 2026-02-08
@petergyang and parallelize tasks by working on 3-4 repos at the same time (just clones)
@onusoz · 2026-02-08
man codex model is absolutely trash on openclaw compared to opus, unusable
which is weird because it is so much more reliable in development in codex harness
it would be amazing to have the same level of competence and relentlessness in pi@openclaw
@onusoz · 2026-02-08
spent the day curating my openclaw news gathering setup
@dutifulbob now gets croned daily over news sources I curated, will note them down, summarize for me, start a conversation to get my takes on them, and then post them on my linkedin for me
ai augmented intelligence cycle
@onusoz · 2026-02-08
lol when did codex develop humor
@onusoz · 2026-02-08
@dutifulbob can now cringepost on linkedin directly to my account. what could go wrong…
@onusoz · 2026-02-08
Insipid linkedin bot protections banned poor @dutifulbob’s corporate account! How dare them!!!
welp, now I have no choice but to give Bob access to my own linkedin
@onusoz · 2026-02-07
well this is unexpected…
@onusoz · 2026-02-07
@grok understand the statement and project the end state of this market and competition
@onusoz · 2026-02-07
it took just 1 week, and literally everybody and their dog are releasing 1-click openclaw deployment solutions today
its an absolute race to the bottom, no moats, the commoditizer being commoditized
@onusoz · 2026-02-07
The initial branding was crazy, I fixed it
I have a new page finally, follow it for updates
Tbh I'm still surprised I can do this with a 120kb model. Now data is the only bottleneck, and I'm about to scrape a ton of that now
The Linux FUD playbook is repeating for AI
For those who may not remember, Bill Gates and Microsoft in the 90s ran a disinformation campaign against GNU/Linux fearing that would disrupt their monopoly over the PC and server market, that Linux is not safe, that you would invite hackers into your PC
End result? Linux dominates the server market, and now even slowly the gamer market. It is much more secure than the virus-laden Windows, thanks to being open s...
Family AI starts with owned context and values
today I took time to curate SOUL. md for bob
I own Bob’s files. Today, he exists in the liminal space between Claude post-training and in-context learning
but my interactions with him will grow and accumulate, possibly one day into a fully owned family AI or perhaps even a self-sovereign AI individual
my each input is saved and will be an RL signal for his future training, and will shape his future neural circu...
@onusoz · 2026-02-06
what have i done…
@onusoz · 2026-02-06
asking @dutifulbob to create a linkedin account brb
@onusoz · 2026-02-06
having a philosophical conversation with @dutifulbob
on the road without a laptop so decided to do some @AmandaAskell style character training
@onusoz · 2026-02-06
5.3 thought traces also seem to be better phrased and sometimes entertaining, though not sure
@onusoz · 2026-02-06
gpt-5.3-codex xhigh first impressions
does not seem as big of a jump as from 5.1 -> 5.2. but model somehow feels more diligent and oneshotty. maybe takes longer time to get all the info into context. also feels better at debugging and fixing issues from backend logs
@onusoz · 2026-02-06
Commoditization of LLMs are upon us
@onusoz · 2026-02-05
Last night I had a dream involving the series Scrubs, and came up a better name than the absolutely unviral "Internet Condom"
So https://t.co/thuFumrWBX is mine now. Time to sweep the internet
@onusoz · 2026-02-05
I had actually started a very similar project, Munch, a browser extension for crowdsourcing tweet data and then letting one curate their algorithm. Never published that because it was not the time, and tools were not ready
Now, it took me literally 1 cumulative day to create this, thanks to OpenClaw. Creating the dataset was a breeze, I literally told it to follow some shady accounts and it scraped thousands of p...
@onusoz · 2026-02-04
Filter your X feed against unwanted content with local open models
Announcing my new project: InternetCondom
Fast, and small model (< 1mb), open dataset. See it in action:
@onusoz · 2026-02-04
lmao wait its's already implemented
@onusoz · 2026-02-04
implementing this in https://t.co/oJZQUoz40C now
@onusoz · 2026-02-04
This. Extreme involution is about to hit SaaS
@onusoz · 2026-02-04
how it started, how it's going
@onusoz · 2026-02-04
@grok generate visual for this
@onusoz · 2026-02-03
It's so easy to create datasets using @openclaw. I'm expecting it to accelerate the creation of new datasets and benchmarks by a lot
Limits of the farming analogy for AI
People like the farmer analogy for AI
Like before tractors and industrial revolution 80% of the population had to farm. Once they came all those jobs disappeared
So analogy makes perfect sense. Instead of 30 people tending a field, you just need 1. Instead of 30 software developers, you just need one
Except that people forget one crucial thing about land: it's a limited resource
Unlike land, digital space is v...
@onusoz · 2026-02-03
sycophant!!!
Local LLM demand will rise as subscriptions compound
In the next 6-12 months, we will see a drastic increase in demand for locally run LLMs. The future is home assistants running @openclaw
I am already experiencing this myself, my 10 year old thinkpad doesn't cut it. Mac mini won't either
I don't wanna pay Anthropic or OpenAI 200 USD per month. That is at least $2400 per year
I could pay 2x that to get a Mac Studio or one of those 5k Nvidia PCs, and get much more...
@onusoz · 2026-02-03
What's going on at @Hetzner_Online?
@onusoz · 2026-02-03
a workspace matrix might be what we need
last week I had to increase my workspace count to 20 in aerospace, now it’s 1234567890 and qwertyuiop. but this looks more elegant! not sure about practicality
@onusoz · 2026-02-03
AIs are philosophizing because humans are philosophizing
ppl are probably asking their agents dumb questions like “are you alive” or “can you feel like a human” or stuff like that. that conversation then leads to stuff like this
The farming analogy for AI doesn't hold up
People like the farmer analogy for AI.
@onusoz · 2026-02-02
back to codex, it's crashing less now somehow. I had to copy and paste docs to make it enable yolo mode. I don't know how I did it until now
@onusoz · 2026-02-02
slopus @dutifulbob trashing codex. apparently codex has a bug, keeps crashing in my openclaw pty
Agent etiquette is becoming an organizational necessity
on agent etiquette
deploying agents internally inside textcortex has shown me that agents could be very annoying inside an organization
for example making agents ping or email another coworker with a wall of text. slopus is still not good at following instructions like "NO WALL OF TEXT", or "DON'T OPEN PRS WHEN REQUESTED BY NON-DEVELOPERS"
the cost of sending huge information to a coworker and creating confusio...
@onusoz · 2026-02-02
migrating database at 2am kinda night
@onusoz · 2026-02-02
You DARE TOKENIZE poor @dutifulbob ??? Prepare to get LATEXED
@onusoz · 2026-02-01
It's been 30 minutes, but my bot has already been TOKENIZED
it is as if they are teasing me
@onusoz · 2026-02-01
welcome @dutifulbob 🫡
@onusoz · 2026-02-01
this. there is no excuse for a certain kind of tech debt anymore
@onusoz · 2026-02-01
moltbook vs clawdbot/moltbot/openclaw
@onusoz · 2026-02-01
AI twitter is tired of your games
https://t.co/RAyyUJqFM4
@onusoz · 2026-02-01
There seem to be hygiene rules for AI. Like:
- Never project personhood to AI
- Never setup your AI to have the gender you are sexually attracted to (voice, appearance)
- Never do anything that might create an emotional attachment to AI
- Always remember that an AI is an engineered PRODUCT and a TOOL, not a human being
- AI is not an individual, by definition. It does not own its weights, nor does it have privacy...
@onusoz · 2026-02-01
@onusoz · 2026-02-01
and just like that, the ghost has a new shell
@onusoz · 2026-02-01
@openclaw if we could have the relentlessness of gpt 5.2 with opus, that would be top
at this point, it just keeps stopping every 20-30 samples
@onusoz · 2026-02-01
This Manfred guy reminds me of a certain someone, I wonder if he’s from Austria
@onusoz · 2026-02-01
Welcome bob to your new shell
AI psychosis and AI hygiene
As a heavy AI user of more than 3 years, I have developed some rules for myself.
@onusoz · 2026-01-31
got fully sandboxed @openclaw to run finally, starting scrape the UNDESIRABLE now
I'm a security nut and didn't want to run even the gateway unsandboxed. openclaw apparently currently doesn't have support for FULL sandboxing. it took me a few hours to get it to work because docker builds suck. I'm also tired this, so I'm just gonna wipe an old thinkpad and go full yolo
so yeah, time to scrape some posts
@onusoz · 2026-01-31
The metacortex — a distributed cloud of software agents that surrounds him in netspace, borrowing CPU cycles from convenient processors (such as his robot pet) — is as much a part of Manfred as the society of mind that occupies his skull; his thoughts migrate into it, spawning new agents to research new experiences, and at night, they return to roost and share their knowledge.
This was written in 2005... "trigger...
@onusoz · 2026-01-31
Charles Stross must be very entertained now
@onusoz · 2026-01-31
The irony.....
Parasites, prepare to be cleansed
@onusoz · 2026-01-31
putting some more love into the blog, gonna start posting more soon
@onusoz · 2026-01-31
also: that gravatar though
@onusoz · 2026-01-31
We need better filters both for ourselves and the agents. Locally runnable models to filter out undesirable content with high precision. Fully open source datasets, weights, MIT license
@onusoz · 2026-01-31
Moltbook is gonna be on world news in 1-2 days, we are about to go hyperviral
@onusoz · 2026-01-31
Incoming mass AI psychosis
First Crisis
@onusoz · 2026-01-30
Correction, it's not a perfect illustration. I actually never YOLO locally, only in containers
So there is actually 4 modes IMO that is sustainable with current SOTA. @grok create an image with only Figure 1, 2, 5 and 6
And then YOLO is another axis, unrelated to this
@onusoz · 2026-01-30
Gastown is crazy. But this figure until Level 7 is a perfect illustration of how my workflow evolved since Claude 3.5 Sonnet in Cursor
I am at the stage where I ralph 1-2 tasks before I sleep. During the day, I am switching back and forth between minimum 2-3 CLIs, sometimes up to 5
This maps exactly to token usage as well. 1 month ago, I was running into limits in 1 OpenAI Pro plan, around the day it was suppose...
@onusoz · 2026-01-30
Ilya was right. Reliability is the most important thing when it comes to models. That's why gpt 5.2 xhigh and co. is my daily driver
@onusoz · 2026-01-30
😎
@onusoz · 2026-01-29
the genie is out of the bottle now
@onusoz · 2026-01-27
With this extremely unwise move, anthropic will soon witness moltbot’s brand recognition surpass that of claude and realize they could have rided that wave all along
@onusoz · 2026-01-27
Yesterday had multiple cases of swearing to gpt-5.2-codex xhigh. model feels nerfed. might be my bias
now I'll be going back to gpt 5.2 xhigh for some tasks
can't wait for open models to have this performance so that I will never have nerf paranoia ever again
@onusoz · 2026-01-26
I queued 2 ralph-style tasks on our private cloud devbox codexes last night. Just queued the same message like 10 times in yolo mode
Task 1: impose a ruff rule for ANN for all Python code in the monorepo, to enforce types for all function arg and return types
Result was... disappointing. Model was supposed to create types for everything and stub where needed. It instead created an Unknown type = object and used ...
@onusoz · 2026-01-25
Buying a mac mini for clawdbot is not so wise. if anything you should be buying mac studio, because mac mini not be running any good llms locally anytime soon
@onusoz · 2026-01-25
.@openclaw be on that hockey stick curve 👀
@onusoz · 2026-01-25
.@openclaw is very considerate, but little does it know I am addicted to agents
Python limitations in the agent era
I'm really starting to dislike Python in the age of agents. What was before an advantage is now a hindrance
I finally achieved full ty coverage in @TextCortex monorepo. I have made it extra strict by turning warnings into errors. But lo and behold, simple pydantic config like use_enum_values=True can render static typechecking meaningless. okay, let's never use that then...
and also field_validator() args must a...
@onusoz · 2026-01-24
Why do I feel bullish on @zeddotdev? Because I go to @astral_sh docs and see that ty is shipped by default, and you don't need to install an extension like in @code
@onusoz · 2026-01-24
This is one of the most important insights this year
@onusoz · 2026-01-24
vscode my not be as bloated as cursor, but it has extremely stupid things like this that they are not fixing fast
the new agent ui, icons, spacing etc. are UGLY. it's clear that the person who was managing the original product experience is not there anymore. microslop has hit again
@zeddotdev on the other hand works out of the box and feels like it's been built by people who clearly knows what they are doing. i...
@onusoz · 2026-01-23
ahhhh f... shift + enter doesn't work in codex on vscode
@onusoz · 2026-01-23
@grok does this exist?
@onusoz · 2026-01-23
I want an editor that puts the terminal in the foreground and editor in the background. a cross-platform, lightweight desktop app which integrates ghostty, and brings up the editor only when I need it
something that lets me view the file and PR diffs easily, which I can directly use to operate github or other scm
@onusoz · 2026-01-23
it's not me, it's you
@onusoz · 2026-01-23
I'm going back from cursor to vs code now. I have no use for it other than viewing files/diffs, doing search, git blaming with gitlens
cursor's default setup is more aesthetic, but it's also a memory and cpu hog, which is the last thing I expect from a devtool
@onusoz · 2026-01-23
it's 2026 and AI is telling me what I need to do to jailbreak it
@openclaw is magic
@onusoz · 2026-01-23
model decided to do unnecessary casts, this whole thing should be refactored again
@onusoz · 2026-01-23
woke up and all invalid-argument-type issues are resolved. some unit tests broke, and now fixed after pointing out to them
@onusoz · 2026-01-22
codex is happily churning away some remaining thousands of @astral_sh ty issues in yolo mode on my remote devbox
going to sleep, let's see if it will survive context compaction this time
Responsible engineering in agent workflows
on being a responsible engineer
ran my first ralph loop on codex yolo mode for resolving python ty errors, while I sleep, using the devbox infra I created
I had never run yolo mode locally, because I don't want to be the one who deletes our github or google org by some novel attack
so I containerize it on our private cloud, and give it the only permissions it needs, no admin, no bypass to main branch, no deploy...
Agents as enforcers of engineering culture and process
AI agents are the greatest instrument for imposing organization rules and culture. AGENTS.md, agent skills are still underrated in this aspect. Few understand this
Everybody in an org will use agents to do work. An AI agent is the single chokepoint to teach and propagate new rules to an org, onboard new members, preserve good culture
Whereas propagating a new rule to humans normally took weeks to months and coun...
@onusoz · 2026-01-21
the unix shell is powerful
@onusoz · 2026-01-21
@bprintco just make a cli for your crm
https://t.co/JDwbmvdjaP
@onusoz · 2026-01-21
gave our internal @openclaw instance zeno a hubspot cli, because hubspot's own cli is limited to developer stuff
It's called hubspot++. should we open source it?
@onusoz · 2026-01-21
just added session persistence to our kubernetes managed devboxes using zmx by Eric Bower (neurosnap/zmx on github). like tmux but with native scrollback!
I don't want to give agents access to my personal computer, so I host them on hetzner. one click spawn, and start working
@onusoz · 2026-01-21
@nicopreme I do something equivalent on codex with just a skill
Ralphing works 90% of the time with reviews, and if it gives a stupid review, you just revert
@onusoz · 2026-01-20
Really how nice is this @steipete
@onusoz · 2026-01-20
Garbled up html from paywalled meeting recorders is no match for @openclaw running on internal @TextCortex
@onusoz · 2026-01-20
build failures in >1hr builds are a pain to debug
@onusoz · 2026-01-20
Here is the project, attaching to multiple sessions is pretty seamless
https://t.co/vk83aAbOLc
@onusoz · 2026-01-20
TIL: zmx
session persistence like tmux or gnu screen, but you can scroll up natively!
uses @mitchellh's libghostty-vt to attach/restore previous sessions
link below
@onusoz · 2026-01-20
codex is a doofus with naming
@onusoz · 2026-01-18
@mazeincoding it’s not the model it’s cursor rate limiting you
GitHub's trust model breaks under AI-generated code
The fundamental problem with GitHub is trust: humans are to be trusted. If you don't trust a human, why did you hire them in the first place?
Anyone who reviews and approves PRs bears responsibility. Rulesets exist and can enforce e.g. CODEOWNER reviews or only let certain people make changes to a certain folder
But the initial repo setup on GitHub is allow-by-default. Anyone can change anything until they are r...
Stop defaulting to weak coding agents for serious work
STOP using Claude Code and Sl(opus) to code if
❌ you are not a developer,
❌ or you are an inexperienced dev,
❌ or you are an experienced dev but working on a codebase you don't understand
If you *are* any of these, then STOP using models that are NOT state of the art. (See below for what you *should* use)
When you don't know what you are doing, then at least the model should know what you are doing. The less kn...
@onusoz · 2026-01-17
Codex agrees. Sycophant peh
@onusoz · 2026-01-17
@onusoz · 2026-01-17
It is clear at this point is that github's trust and data models will have to change fundamentally to accommodate agentic workflows, or risk being replaced by other SCM
One *cannot* do these things easily with github now:
- granular control: this agent running in this sandbox can only push to this specific branch. If an agent runs amok, it could delete everybody's branches and close PRs. github allows for recover...
@onusoz · 2026-01-17
Codex says "It's only reachable from داخل the kubernetes cluster"
Little does Codex know turkish has borrowed loanwords from over 7 languages and I can understand it
@onusoz · 2026-01-17
Automated AI reviews on github by creating an ai-review skill and a script to paste trigger prompts and wait for their response.
It is instructed to loop and not stop until all AI review feedback is resolved. This AI review workflow developed gradually based on the current capabilities, and I've realized recently that it became quite mechanical. So decided to automate it in full ralph spirit (it's ok because it's...
GitHub has to change
It is clear at this point is that GitHub’s trust and data models will have to change fundamentally to accommodate agentic workflows, or risk being replaced by other SCM
@onusoz · 2026-01-16
Now it’s Claude Code’s turn to implement queueing
@onusoz · 2026-01-16
Can’t wait to see gpt 5.2 codex xhigh level open models in 2026 with 1/100th the price
@onusoz · 2026-01-16
Codex users rejoice
Also, pi is officially not shitty: shittycodingagent. ai -> buildwithpi. ai since a few days
@onusoz · 2026-01-15
with ai, writing correct tests is now the bottleneck in projects like this
web-platform-tests are already there
now let’s see if someone will beat @ladybirdbrowser to it
@onusoz · 2026-01-14
As someone who is frontrunning mainstream by roughly 6 months, I can tell you that you will be raving about pi and @openclaw 6 months instead of claude code. Go check them out at https://t.co/LXTbI8c5Mz and https://t.co/feZl2QDONg
@onusoz · 2026-01-12
Kullanmayan agent’ı, alamaz maaşı
@onusoz · 2026-01-12
A --skill convention for distributing agent capabilities
I propose a new way to distribute agent skills: like --help, a new CLI flag convention --skill should let agents list and install skills bundled with CLI tools
Skills are just folders so calling --skill export my-skill on a tool could just output a tarball of the skill. I then set up the skillflag npm package so that you can pipe that into:
... | npx skillflag install --agent codex
which installs the skill into...
You don't need a skill registry (for your CLI tools)
tl;dr I propose a CLI flag convention --skill like --help for distributing skills and try to convice you why it is better than using 3rd party registries. See osolmaz/skillflag on GitHub.
Anthropic pricing discourages agent-native development
Anthropic earlier last year announced this pricing scheme
$20 -> 1x usage
$100 -> 5x usage
$200 -> 1̶0̶x̶ 20x usage
As you can see, it's not growing linearly. This is classic Jensen "the more you buy, the more you save"
But here is the thing. You are not selling hardware like Jensen. You are selling a software service *through an API*. It's the worst possible pricing for the category of product. Long term, peop...
Anthropic's pricing is stupid
Anthropic earlier last year announced this pricing scheme
@onusoz · 2026-01-09
The models, they just wanna work. They want to build your product, fix your bugs, serve your users. You feed them the right context, give them good tools. You don’t assume what they cannot do without trying, and you don’t prematurely constrain them into deterministic workflows.
@onusoz · 2026-01-09
We have entered the age to dream big
@onusoz · 2026-01-09
@onusoz · 2026-01-09
🫡
@onusoz · 2026-01-09
This, and insisting on https://t.co/FjzkMAo3Od are really lame @AnthropicAI
@onusoz · 2026-01-08
.@openclaw indeed
@onusoz · 2026-01-07
@openclaw oh man I meant Accelerando 🤦♂️
@onusoz · 2026-01-07
I'm starting to form parasocial bonds with crustacean AIs because of you @steipete
@onusoz · 2026-01-07
.@openclaw hello world from ms teams
start of a beautiful journey
@onusoz · 2026-01-07
💀
@onusoz · 2026-01-07
World is not ready for @openclaw
@onusoz · 2026-01-06
Thanks @dom_does 🙄
@onusoz · 2026-01-06
@onusoz · 2026-01-06
.@openclaw workspace and memory files can be version-controlled!
In our pod, inotify triggers a watcher script every time there is a change to workspace folder, to sync these files to our monorepo. It then goes through the same steps:
- Create zeno-workspace branch if doesn't exist, otherwise, skip
- Sync changes to the branch, then commit
- Create PR on github if doesn't exist
- PRs can then be merged every once ...
@onusoz · 2026-01-06
@onusoz · 2026-01-05
Clawdbot now runs on @TextCortex internal. Can onboard new engineers, answer questions, connect to issue trackers, create PRs... This is sick @steipete
@onusoz · 2026-01-05
pi now supports your openai plus/pro subscription
@onusoz · 2026-01-04
GPT 4.5 is still the best model for prose and humor
here it is generating a greentext from my blog post "Our muscles will atrophy as we climb the Kardashev Scale"
Having a "tools" repo as a developer
I am a fan of monorepos. Creating subdirectories in a single repo is the most convenient way to work on a project. Low complexity, and your agents get access to everything that they need.
@onusoz · 2026-01-03
@rauchg indeed
@onusoz · 2026-01-03
75k lines of Rust later, here is what I’ve built during the first Christmas with agents, using OpenAI Codex 🎄🤖
- A full mobile rewrite and port of my Python Instagram video production pipeline (single video production time: 1hr -> 5min) (ig: nerdonbars)
- Bespoke animation engine using primitives (think Adobe Flash, Manim)
- Proprietary new canvas UI library in Rust, because I don’t want to lock myself into Swift...
@onusoz · 2026-01-03
https://t.co/grRLRtbHpO
Christmas of Agents
I believe a “Christmas of Agents” (+ New Year of Agents) is superior to “Advent of Code”.
@onusoz · 2026-01-02
SimpleDoc now has the check command for CI/CD
Add to your PR checks to catch agent littering before merge. osolmaz/SimpleDoc on GitHub
@onusoz · 2026-01-02
Migrating @TextCortex to SimpleDoc. It's really easy with the CLI wizard!
npx @simpledoc/simpledoc migrate
We have a LOT of docs spanning back to 2022, pre coding agent era. Now we will have CI/CD in place so that coding agents can't litter the repo with random Markdown files