OleksandrC

As usual, I suppose :) - by filing bug reports, and opening pull requests.

Generally, the models seem to adapt really well. I am using GPT models in hax a lot, and they have no trouble whatsoever using hax tools instead of their "native" codex tools. Also since hax…

The main reason to use C is that it's the easiest way to achieve minimal resource footprint. Also it's the language I know really well already. The demo was recorded with asciinema.

I will leave this here: https://usehax.dev/ GitHub repo: https://github.com/OleksandrChekhovskyi/hax This is a coding agent implementation I am working on, which…

I am working on an agent implementation that you might like: https://github.com/OleksandrChekhovskyi/hax Written in C, tiny footprint, minimalist approach to system prompt and to…

This would be an interesting use case. But it seems API access is not included in the subscription? The value proposition would have been higher if it was (so one subscription for both human and agent…

They could, for example: 1. Rely on users flagging suspected repos (with human moderators reviewing afterwards). 2. Deploying AI agents to evaluate repos against known AI-generated-code patterns (also…

Claude-written code is quite easy to spot - because it has this particular style of overly verbose "walls of text" comments, that 1. repeat verbatim what the code just below does, 2. include…

Recent Kimi K3 release is supposedly frontier-grade, so would be interesting to see what it really costs to run inference for models of this class, when the weights get released and other independent …

One significant advantage of Codex subscription over Claude is that you can use any agent harness with it. Meanwhile Anthropic insists that Claude subscription must only be used with Claude Code itsel…

The article makes a point about agent harnesses being sticky (the supposed moat). I have been building my own agent harness for a while, and I can tell with confidence that the harness almost does not…

The article is rather light on "what to actually do about it". Even the basic "run it in isolated container without access to anything it does not need for the task" would have alr…

The code written by agents generally seems to reflect what you (the human driver) asked for. If you discuss the approach and architecture first, asking the right questions in the process, and then let…