Viewing profile — m3h

Someone who until yesterday did not seem bothered by his technology being possibly used to bomb elementary girls school in another country seems to suddenly care about the repressi…

Is there a specific list of changes they made to the system prompt? They're claiming they removed 80% of it. That's quite substantial. It would be good to know what the model knows…

A while back, I saw a similar feature land in Codex (I'm using the VS Code plugin) but it got removed quickly. What is the chance that an LLM recommended this same idea to the Clau…

> Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters. This puts them on the top of the largest open models list: Kimi K3 2.8T DeepSeek-V4-Pro 1.6T (49B acti…

The author shared their experience building the first version in a month: https://themackabu.dev/blog/js-in-one-month And then the follow up few months later: https://themackabu.de…

[dead]

We have an official pelican on a bicycle from the OpenAI livestream: https://imgshare.cc/mz9xwut3

The speed up numbers based on their testing: Codebase | TypeScript 6 | TypeScript 7 | Speedup ------------|--------------|--------------|-------- vscode | 125.7s | 10.6s | 11.9x se…

When I reviewed the conversations affected by this issue, they did not always align with my feeling of "degraded output". Some were definitely below par, and I recall having to ite…

Indeed, it looks like my work has suffered from the clustering issue as well: reasoning_output_tokens count percent ━━━━━━━━━━━━━━━━━━━━━━━━━ ━━━━━━━ ━━━━━━━━━ 0 873 28.5948 ──────…

Also, kudos to the Z.ai team for adding Linux support from day one.

Z.ai documents integrations with nearly all the popular CLI-based agents: https://docs.z.ai/devpack/tool/others If you're already used to your TUI coding agent, you don't need the …

Correct. Albeit the nuance here is that a more capable model might solve problems more efficiently and faster, possibly saving you tokens. As with any new model, you won't know the…

I didn't realize GPT 5.3 Codex was that good. OpenAI claims to have made their new Terra model as good as GPT 5.5, but with half the cost per intelligence. Hopefully, this will bri…

I think you should try an OpenAI model like GPT 5.5. It is better at following instructions and boundaries set during prompt. It feels like a more capable "agent assistant" than Cl…

Important to note: "Sonnet 5 is an upgrade to Sonnet 4.6, but it uses an updated tokenizer that changes how the model processes text to improve performance (this is similar to the …

Why is Claude Sonnet 5 allowed to be released but OpenAI Terra not? Are they not the same class of models?

If GPT-5.6 preview is not available outside US government approved "trusted partners", I don't see how the General Available can be trusted later. Who knows what they will fix, blo…