Hacker News Reader

Comment by CSMastermind | Hacker News Reader

I find myself using 4o more than o1. I haven't noticed any meaningful improvement from o1 and it has more limitations.

o1 is much much much better at mathematics. I am am a phd student and sometimes give it small problems to play around with, just to get some inspiration. That's the thing: It actually plays around and tries stuff instead of just spitting out a remembered answer like GPT-4o.

I pretty much only use o1 for more rigorous tasks (coding/math). Eg the other day I gave it the tax rates for my area and used it to explore different tax scenarios

In my experience, o1 is much better at assisting sotware architectual planning and also bug finding. For other tasks, it's unfortunately too slow for the benefits it provides. 4o and sonnet are net better in terms of speed/value balance.

I'm finding o1 to be far better at code. I wonder why people are having such differences

Interesting. I've tried to use it for a few things, it works where I'd expect -- make a scaffolding for a simple Java project, edit this English -- but whenever I then try to use it for Real Work, things that require some thought and don't have lots of examples in the training set, it fails. It didn't help me as much implementing some ideas from an academic paper about compilers, or on using AF_XDP sockets.

It's interesting that it has the property of always returning _something_, so you have to be careful how you phrase. And the something returned will be optimized for looking right, but might only be so by accident.

I’ve found o1 can be more hit-or-miss than the relatively consistent 4o, but o1 tends to be better at solving really hairy problems.

In an apples to apples comparison, 4o can overlook important things while focusing on the kernel of the problem, while o1 is often more comprehensive.

o1 annoys the hell out of me. it ignores my custom instructions, and after using a highly customized gpt-4 for a while I can't bear the blandness of the default models anymore.

it doesn't swear or yell at me, it's verbose, apologetic, overly correct in its language, gives me endless bulleted lists that convey little information.

unbearable.

Reply on news.ycombinator.com