Hacker News: lenglainhttps://news.ycombinator.com/user?id=lenglainHacker News RSShttps://hnrss.org/hnrss v2.1.1Mon, 17 Aug 2026 07:29:07 +0000<![CDATA[New comment by lenglain in "Why does Opus 5 feel worse to work with?"]]>Am I crazy for thinking that this is a pretty big regression compared to past models? I remember being blown away by GPT 4.5, and I kept using it up until they decommisioned it. I think claude 3.7 sonnet was pretty good too. Gemini seems to be the best one right now for actually talking. Opus is top tier for code but when i talk to it I want to rip my hair out. GPT-5.6 is doing best for me right now among the powerful models.

]]>Sun, 16 Aug 2026 17:14:23 +0000https://news.ycombinator.com/item?id=49321820lenglainhttps://news.ycombinator.com/item?id=49321820https://news.ycombinator.com/item?id=49321820<![CDATA[New comment by lenglain in "Cloudlflare builds OAuth with Claude and publishes all the prompts"]]>I have had no issues with LLMs trying to force a language on me. I tried the whole snake game test with ChatGPT but Instead of using Python I asked it to use the nodejs bindings for raylib, which is rather unusual.

It did it in no time and no complaints.

]]>Wed, 04 Jun 2025 13:04:04 +0000https://news.ycombinator.com/item?id=44180323lenglainhttps://news.ycombinator.com/item?id=44180323https://news.ycombinator.com/item?id=44180323