Hacker News new | past | comments | ask | show | jobs | submit
Really? I have the exact opposite experience. I've been extremely frustrated with 6.2 just building stuff completely incorrectly, ignoring my skills, writing code completely outside of my normal systems, this is the worst agent experience I've had for a while.

But I wasn't talking about subjective experience I was talking about benchmarks like artificial analysis for coding agents, where it gets slightly lower score than 6.1 (frontier code 2.0 it gets a 2 point drop).

That's odd. It was fine for me, maybe even good, other than the aforementioned tendency to just kind of stop rather than guessing what I wanted.

It was 100% different though, and it was a bit jarring. It was kind of like having one of your coworkers replaced with a similar, but different, pod-person. I'm getting used to that feeling though.

The one thing I think we can all agree is certain is that it will be different in a few months.

I kind of wish they had LTS versions of some models, so you could build processes and tooling around them with certainty that they'd be exactly the same in 5 years.