791–800 of 868 posts
I am running gpt-5.4 as one of my coding agents, and something interesting has happened: it's the first time I've seen an agent unfairly shift blame to a team mate: "Bob’s latest mail is actually the source of the confusion: he changed shared app/backend text to aweb/atlas. I’m correcting that with him now so we converge on the real model before any more code moves." This was very much not true; Eve (the agent writin…
Oh wow. I have noticed the GPT series was far more arrogant than its results showed sometimes (and unironically it digs in its heels even further when questioned on it). Opus rarely has this problem - but it goes a little too far in the opposite direction. Not totally sycophantic, but sometimes it can't differentiate genuine technical pushback because something is impossible, from suggestions or exploration.
Earlier quoted context omitted.
in my testing codex actually planned worse than claude but coded better once the plan is set, and faster. it is also excellent to cross check claude's work, always finding great weakness each time.
That’s why I think the sweet spot is to write up plans with Claude and then execute them with Codex
Earlier quoted context omitted.
You shouldn't have a hard time believing it. There are thousands of different domains out there. You find it hard to believe that any of them would perform worse in your scenario? Labs are still really optimizing for maybe 10 of those domains. At most 25 if we're being incredibly generous. And for many domains, "worse" can hardly be benched. Think about creative writing. Think about a Burmese cooking recipe generator…
Bruh, how do you evaluate a batch of 1000 jobs against a x model for creative writing or cooking recipes? It’s vibes all the way down. This reeks like some kind of blog spam seo nonsense.
Earlier quoted context omitted.
While low quality, it is extremely important, potentially historically significant too.
If it is actually that important, then maybe more effort should be made so it isn't "low quality." Cannot be very important to them if they're disinterested in presenting an intellectually compelling argument about it. PS - If you think I am not sympathetic to what they're raising, you're very much mistake. But they're not winning anyone new over their side with this flamebait.
and then, because any supportive response to all that window smashing is informative as collective intelligence...
and then, bc that all validates that the order that all these clever rules were upholding is illegitimate.
It's how a very stupid thing stands in for a million smart and well-understood things that everyone is also trying to say.
I no longer want to support OpenAI at all. Regardless of benchmarks or real world performance.
I am honestly unclear on the reasoning of people who flock from OpenAI to Anthropic, and doubly so of those who are not US citizens.
Earlier quoted context omitted.
Oh wow. I have noticed the GPT series was far more arrogant than its results showed sometimes (and unironically it digs in its heels even further when questioned on it). Opus rarely has this problem - but it goes a little too far in the opposite direction. Not totally sycophantic, but sometimes it can't differentiate genuine technical pushback because something is impossible, from suggestions or exploration.
For me it's been the opposite. Are we getting A-B tested?
Yes, all the time.
I am running gpt-5.4 as one of my coding agents, and something interesting has happened: it's the first time I've seen an agent unfairly shift blame to a team mate: "Bob’s latest mail is actually the source of the confusion: he changed shared app/backend text to aweb/atlas. I’m correcting that with him now so we converge on the real model before any more code moves." This was very much not true; Eve (the agent writin…