Earlier quoted context omitted.
how do you make them chat with each other?
It's text submitted to APIs. Not real conversations.
It's air molecules vibrated by mucous membranes. Not real conversations.
GPT-5.4
801–810 of 868 posts
Re: GPT-5.4
#802lol yet another pat on their own backs without comparison to other frontier models.
Also, the timing of this release, 5.3 and 5.2, relative to the other releases, feels more like a bug fix than something "new"
Re: GPT-5.4
#803Earlier quoted context omitted.
Weird, I have had the opposite experience. Codex is good at doing precisely what I tell it to do, Opus suggests well thought out plans even if it needs to push back to do it.
This is just the stochastic nature of LLM's at play. I think all of the SOTA models are roughly equivalent, but without enough samples people end up reading into it too much.
I used to feel like you do, but I don't agree. I would just say it is not consistent. For a given codebase and given goal, sometimes Claude will be the more sensible, creative, thoughtful planner and sometimes Codex will be, sometimes Claude will make a serious oversight that Codex catches and sometimes the opposite. But the trend for me and seemingly a lot of people is that Claude is a more "human-like/human-smart" planner than Codex (in a positive way) but is more likely to make mistakes or forget details when implementing major codebase changes.
Re: GPT-5.4
#804I remember in a video Sam Altman said they didn’t want to publish GPT versions like Apple does, but they are actually doing it now.
Re: GPT-5.4
#805I 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.
Opus has a different sort of arrogance. It readily admits fault, but at the same time is quick to declare its new code as the greatest thing since sliced bread. If you let it write commit messages itself, it's almost comical how much it toots its own horn.
Re: GPT-5.4
#806So let me get this straight, OpenAi previously had an issue with LOTS of different models snd versions being available. Then they solved this by introducing GPT-5 which was more like a router that put all these models under the hood so you only had to prompt to GPT-5, and it would route to the best suitable model. This worked great I assume and made the ui for the user comprehensible. But now, they are starting to in…
> I’m so glad I am not a Chat user, because this adds so much unnecessary cognitive load. Yeah having Auto selected is really destroying my cognitive load...
If you find that auto is doing a good job, your expectations must be so low and you must be so uncritical
Re: GPT-5.4
#807Earlier quoted context omitted.
Big fan of OpenAI and recently swapped over due to their recent policies. Will never use Anthropic again. I think GPT-5 is better and I like the companies values.
which values of OpenAI do you prefer and which values of Anthropic do you dislike? out of curiousity
Don't feed the trolls
Re: GPT-5.4
#808I 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…
interestingly, Claude has been doing this for me a lot but most often just saying this like "Looks like your coworker was misunderstanding this feature..." not really shifting blame but more like pointing out things
Re: GPT-5.4
#809I 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…
This is awesome. So your job as a tech lead or agent manager is to make sure the "team" plays nice and stays productive. I wonder if an agent can feel resentment towards another agent, just like a human would. Is there an HR agent that can mitigate the conflict :)
Re: GPT-5.4
#810Earlier quoted context omitted.
It's a little hard to compare, because Claude needs significantly fewer tokens for the same task. A better metric is the cost per task, which ends up being pretty similar. For example on Artificial Analysis, the GPT-5.x models' cost to run the evals range from half of that of Claude Opus (at medium and high), to significantly more than the cost of Opus (at extra high reasoning). So on their cost graphs, GPT has a con…
Looks like the same thing might apply to GPT-5.4 vs the previous GPTs: >In the API, GPT‑5.4 is priced higher per token than GPT‑5.2 to reflect its improved capabilities, while its greater token efficiency helps reduce the total number of tokens required for many tasks. I eagerly await the benchies on AA :)
Benchies update:
https://artificialanalysis.ai/
Looks like it costs ~25% more than 5.2, with both on xhigh reasoning.
They only seem to have tested xhigh, which is a shame, since I think that reasoning level is in the point of diminishing returns for most tasks.
Also I was completely wrong earlier. Opus is significantly more expensive. I was looking at the wrong entry in the chart, the non-reasoning version of Opus. The fair comparison is Opus on max reasoning, which costs about twice the price of GPT-5.4 xhigh, to run the AA evals.