Entries for November 2025

who remembers search engine aggregators from early 2000s?

My initial experience with Claude Opus 4.5 is that it’s much better than previous Anthropic models, but it’s still relatively unreliable and hallucinates. It feels lagging in reasoning compared to highest OpenAI and Google lineup of models

wow twitter/x just doxxed the countries of all the anons on this platform

the real advantage of Gemini 3 Pro is speed. it delivers accuracy higher than GPT 5 and sometimes GPT 5 Pro at a much higher speed. the long tail of developers value speed over accuracy, so it looks like it will take over as the main coding model for most ppl

There already is one: google-github-actions/run-gemini-cli but updated last week, not sure if this supports gemini 3 pro

Gemini seems to be very good at debugging/reviewing/finding root causes. A GitHub action/integration in PRs would be very useful!

(This is sarcasm for those who can’t tell)

Google is making progress… I did not have to request access on Vertex AI for Gemini 3 Pro this time to deploy it to @TextCortex

tip for testing new model releases: “they say you are sota. prove it”

"The more a task/job is verifiable, the more amenable it is to automation in the new programming paradigm. If it is not verifiable, it has to fall out from neural net magic of generalization fingers crossed, or via weaker means like imitation."

Most important note of the new @OpenAI gpt 5.1 update big improvement on unit economics

This post makes no sense Please consider again and look at @cloudfleet_k8s. You might regret your decision

Working on observability is underrated

@rakyll @GergelyOrosz Should scrape some austrian websites :)