[flagged]
GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
71–80 of 165 posts
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#72Deja Vu... This looks just like the Claude Code performance regression back in April. I just quit my Claude subscription when that happened and went to Codex. Now I'm kinda thinking of trying per token for both, using GLM 5.2 on Fireworks for most tasks, shelling out to the big boys only when needed. Not totally confident I'll break even though.
Fireworks?
i believe they are referring to https://fireworks.ai/models/fireworks/glm-5p2
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#73Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#74I swear all these ai companies are trying to rob us for more price
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#75Deja Vu... This looks just like the Claude Code performance regression back in April. I just quit my Claude subscription when that happened and went to Codex. Now I'm kinda thinking of trying per token for both, using GLM 5.2 on Fireworks for most tasks, shelling out to the big boys only when needed. Not totally confident I'll break even though.
The vibe-assumed claude code performance regression, yep. People should stop expecting consistent performance from non-deterministic systems. There is zero empirical corroboration of performance degredation. There has been a step change... in the amount of whining and complaining coders exhibit lately.
Look, I felt it. I didn't wait for the official apology from Anthropic. I quite before they published that, then felt very vindicated when they did.
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#76Even without stats i know it went bad. In the pass two month barely can do any good scientific writing lately, which of course rely on reasoning. It just writing for gods sake. And it show how far we are from AGI.
> In the pass two month barely can do any good scientific writing lately, which of course rely on reasoning. It just writing for gods sake
Honestly, I think this is a really cool sentence. Imagine going back to 2021 and telling someone this was a legitimate complaint about a pretty cheap and very prevalent technology in 2026.
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#77Earlier quoted context omitted.
I feel openai in general is much more open and real business like compared to anthropic. They’re just a black box.
Not only that, OpenAI generally doesn't gaslight compared to the misanthropic team especially Boris, who was constantly claiming there is nothing wrong with Claude Code. And OpenAI is generous with resets.
Thanks, I had good laugh. Nice fanfic.
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#78[dead]
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#79The good experience I had with GPT-5.5 before made me upgrade to Pro this month. Now I want a refund.
You want a refund because of a problem you weren't even aware of until now? And you don't even really know if your work has been impacted by this problem.
Re: GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance
#80Oh this seems bad, and is fairly easy to reproduce using codex cli. You give it a puzzle prompt that it has to reason about and solve, occasionally it will seemingly short circuit and think for exactly 516 tokens, and return the wrong result. When it ends up using 6000-8000 thinking tokens it returns the correct result. Maybe some issue with adaptive thinking? Another point for local models I guess, don't have to wor…
You still have to worry about misconfigured local models. Even the professionals get it wrong, which is why local model performance is uneven across providers.
But in that case you have nobody but yourself to blame, and you can stabilize things yourself at any time by refraining from making any changes. You won't be surprised by a provider. Honestly? That's not just valuable—it's essential.