281–290 of 868 posts
I no longer want to support OpenAI at all. Regardless of benchmarks or real world performance.
i just HATE talking to it like a chatbot
idk what they did but i feel like every response has been the same "structure" since gpt 5 came out
feels like a true robot
I use ChatGPT primarily for health related prompts. Looking at bloodwork, playing doctor for diagnosing minor aches/pains from weightlifting, etc. Interesting, the "Health" category seems to report worse performance compared to 5.2.
I've done the same, and I tested the same prompts with Claude and Google, and they both started hallucinating my blood results and supplement stack ingredients. Hopefully this new model doesn't fall on this. Claude and Google are dangerously unusable on the subject of health, from my experience.
Earlier quoted context omitted.
That's an interesting point regarding context Vs. compaction. If that's viewed as the best strategy, I'd hope we would see more tools around compaction than just "I'll compact what I want, brace yourselves" without warning. Like, I'd love an optional pre-compaction step, "I need to compact, here is a high level list of my context + size, what should I junk?" Or similar.
This is exactly how it should work. I imagine it as a tree view showing both full and summarized token counts at each level, so you can immediately see what’s taking up space and what you’d gain by compacting it. The agent could pre-select what it thinks is worth keeping, but you’d still have full control to override it. Each chunk could have three states: drop it, keep a summarized version, or keep the full history.…
The marquee feature is obviously the 1M context window, compared to the ~200k other models support with maybe an extra cost for generations beyond >200k tokens. Per the pricing page, there is no additional cost for tokens beyond 200k: https://openai.com/api/pricing/ Also per pricing, GPT-5.4 ($2.50/M input, $15/M output) is much cheaper than Opus 4.6 ($5/M input, $25/M output) and Opus has a penalty for its beta >200…
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 considerable distribution, and Opus sits right in the middle of that distribution.
The most striking graph to look at there is "Intelligence vs Output Tokens". When you account for that, I think the actual costs end up being quite similar.
According to the evals, at least, the GPT extra high matches Opus in intelligence, while costing more.
Of course, as always, benchmarks are mostly meaningless and you need to check Actual Real World Results For Your Specific Task!
For most of my tasks, the main thing a benchmark tells me is how overqualified the model is, i.e. how much I will be over-paying and over-waiting! (My classic example is, I gave the same task to Gemini 2.5 Flash and Gemini 2.5 Pro. Both did it to the same level of quality, but Gemini took 3x longer and cost 3x more!)
The marquee feature is obviously the 1M context window, compared to the ~200k other models support with maybe an extra cost for generations beyond >200k tokens. Per the pricing page, there is no additional cost for tokens beyond 200k: https://openai.com/api/pricing/ Also per pricing, GPT-5.4 ($2.50/M input, $15/M output) is much cheaper than Opus 4.6 ($5/M input, $25/M output) and Opus has a penalty for its beta >200…
There is extra cost for >272K: > For models with a 1.05M context window (GPT-5.4 and GPT-5.4 pro), prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex. Taken from https://developers.openai.com/api/docs/models/gpt-5.4
[flagged]
Earlier quoted context omitted.
You may want to look over this thread from cperciva: https://x.com/cperciva/status/2029645027358495156 I too tried Codex and found it similarly hard to control over long contexts. It ended up coding an app that spit out millions of tiny files which were technically smaller than the original files it was supposed to optimize, except due to there being millions of them, actual hard drive usage was 18x larger. It seemed…
Please don't post links with tracking parameters (t=jQb...). https://xcancel.com/cperciva/status/2029645027358495156
Feels like a losing battle, but hey, the audience is usually right.
The marquee feature is obviously the 1M context window, compared to the ~200k other models support with maybe an extra cost for generations beyond >200k tokens. Per the pricing page, there is no additional cost for tokens beyond 200k: https://openai.com/api/pricing/ Also per pricing, GPT-5.4 ($2.50/M input, $15/M output) is much cheaper than Opus 4.6 ($5/M input, $25/M output) and Opus has a penalty for its beta >200…
Like, if you really don’t want to spend any effort trimming it down, sure use 1m.
Otherwise, 1m is an anti pattern.