501–510 of 868 posts
Earlier quoted context omitted.
The latest research these days is that including an AGENTS.md file only makes outcomes worse with frontier models.
:( how can i get claude to always make sure it prettier-s and lints changes before pushing up the pr though?
I've only used 5.4 for 1 prompt (edit: 3@high now) so far (reasoning: extra high, took really long), and it was to analyse my codebase and write an evaluation on a topic. But I found its writing and analysis thoughtful, precise, and surprisingly clearly written, unlike 5.3-Codex. It feels very lucid and uses human phrasing. It might be my AGENTS.md requiring clearer, simpler language, but at least 5.4's doing a good…
The latest research these days is that including an AGENTS.md file only makes outcomes worse with frontier models.
I've only used 5.4 for 1 prompt (edit: 3@high now) so far (reasoning: extra high, took really long), and it was to analyse my codebase and write an evaluation on a topic. But I found its writing and analysis thoughtful, precise, and surprisingly clearly written, unlike 5.3-Codex. It feels very lucid and uses human phrasing. It might be my AGENTS.md requiring clearer, simpler language, but at least 5.4's doing a good…
The latest research these days is that including an AGENTS.md file only makes outcomes worse with frontier models.
You shouldnt put things in AGENTS.md that it could discover on its own, you shouldnt make it any larger than it has to be, but you should use it to tell it things it couldnt discover on its own, including basically a system prompt of instructions you want it to know about and always follow. You don't really have any other way to do those things besides telling it every time manually.
Earlier quoted context omitted.
Google is already sending notices that the 2.5 models will be deprecated soon while all the 3.x models are in preview. It really is wild and peak Google.
Like building on quicksand for dependencies. I guess though the argument is that the foundation gets stronger over time
"GPT‑5.4 interprets screenshots of a browser interface and interacts with UI elements through coordinate-based clicking to send emails and schedule a calendar event." They show an example of 5.4 clicking around in Gmail to send an email. I still think this is the wrong interface to be interacting with the internet. Why not use Gmail APIs? No need to do any screenshot interpretation or coordinate-based clicking.
Earlier quoted context omitted.
> or have zero insurances that the model doesn't get discontinued within weeks Why are you using the same model after a month? Every month a better model comes out. They are all accessible via the same API. You can pay per-token. This is the first time in, like, all of technology history, that a useful paid service is so interoperable between providers that switching is as easy as changing a URL.
If you're trying to use LLMs in an enterprise context, you would understand. Switching models sometimes requires tweaking prompts. That can be a complete mess, when there are dozens or hundreds of prompts you have to test.
I no longer want to support OpenAI at all. Regardless of benchmarks or real world performance.
Recent SWE-bench Verified scores I’m watching:
Claude 4.5 Opus (high reasoning): 76.8
Gemini 3 Flash (high reasoning): 75.8
MiniMax M2.5 (high reasoning): 75.8
Claude Opus 4.6: 75.6
GPT-5.2 Codex: 72.8
Source: https://www.swebench.com/index.html
By the way, in my experience the agent part of Codex CLI has improved a lot and has become comparable to Claude Code. That is good news for OpenAI.