Re:The Unreasonable Effectiveness of an LLM Agent Loop with ...
by manmal on Thursday May 15, 2025 @05:38PM
(#43999569)
o3 is shockingly good actually. I can’t use it often due to rate limiting, so I save it for the odd occasion. Today I asked it how I could integrate a tree of Swift binary packages within an SDK, and detect internal version clashes, and it gave a very well researched and sensible overview. And gave me a new idea that I‘ll try.
[ Parent
| on HN ]
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ...
by kenjackson on Thursday May 15, 2025 @06:30PM
(#44000022)
I use o3 for anything math or coding related. 4o is good for things like, "my knee hurts when I do this and that -- what might it be?"
Re:The Unreasonable Effectiveness of an LLM Agent Loop with ...
by TeMPOraL on Friday May 16, 2025 @03:51AM
(#44002814)
In ChatGPT, at this point I use 4o pretty much only for image generation; it's the one feature that's unique to it and is mind-blowingly good. For everything else, I default to o3.
For coding, I stick to Claude 3.5 / 3.7 and recently Gemini 2.5 Pro. I sometimes use o3 in ChatGPT when I can't be arsed to fire up Aider, or really need to use its search features to figure out how to do something (e.g. pinouts for some old TFT screens for ESP32 and Raspberry Pi, most recently).