News for hackers. Stuff that matters.
Re:GPT‑6.2 Astra and Sol by jorl17 on Tuesday November 17, 2026 @01:18PM (#50535774)
I really want GPT models to be good, but Sol models are so slow I cannot use them. Maybe the 500$ subscription (or enterprise packages) are better, but it is unbearably slow. I've tried the fast variant and low reasoning levels and there isn't a significant improvement.

Couple that with the lack of reasoning traces, and I cannot even have a clue what the model is doing while it is working. This is perfectly fine for when we are developing with care for the code (in which case I will know what it is doing by reviewing the output), but not for purely vibe-coding scenarios. And the thing is....if I care about the code...I'd rather trust Opus or Fable.

Re:GPT‑6.2 Astra and Sol by ativzzz on Tuesday November 17, 2026 @01:23PM (#50535859)
Does speed really matter? Most of the time I get the AI to do something, I immediately switch to another one of my things I have in progress and then come back at some point later. I'm never sitting there waiting for it to finish
Re:GPT‑6.2 Astra and Sol by edvardas on Tuesday November 17, 2026 @01:29PM (#50535969)
Personally, my cognitive RAM is limited, so I'd rather work on a few tasks at a time.

The speed is not a big deal - Sol works just fine, but I find it a lot more fun to work with Opus due to its speed

Re:GPT‑6.2 Astra and Sol by Pedro_Ribeiro on Tuesday November 17, 2026 @01:30PM (#50535974)
It depends on the task. For frontend work, for example, it's table stakes.
Re:GPT‑6.2 Astra and Sol by treis on Tuesday November 17, 2026 @01:31PM (#50535995)
It'd be a lot better if you didn't have to switch. It's not nearly there for coding tasks but for other things instant responses are a game changer.
Re:GPT‑6.2 Astra and Sol by jorl17 on Tuesday November 17, 2026 @01:33PM (#50536024)
It depends on the project and task, but for the kinds of projects I'm throwing at it, it matters quite a lot.

The difference is quite staggering. I swap Anthropic and OpenAI models around when tokens run out, and I can do 10x the amount of work on Anthropic's models. Plus, like I said, I can periodically sort of see what it is thinking. It doesn't just say "Recent potato tests caught an off-by-apples error. Regression tests are being written and the gate will run again. I will not call this ready until tests reach expected coverage" every 5 minutes. Sure, it spits claudese, but I'd rather have claudese to parse than this OpenAI nothing-burger of a report.