[sambaumann]

I feel like this has gotten much worse since they were introduced. I guess they're optimizing for verbosity in training so they can charge for more tokens. It makes chat interfaces much harder to use IMO.

I tried using a custom instruction in chatGPT to make responses shorter but I found the output was often nonsensical when I did this

[gs17]

Yeah, ChatGPT has gotten so much worse about this since the GPT-5 models came out. If I mention something once, it will repeatedly come back to it every single message after regardless of if the topic changed, and asking it to stop mentioning that specific thing works, except it finds a new obsession. We also get the follow up "if you'd like, I can also..." which is almost always either obvious or useless.

I occasionally go back to o3 for a turn (it's the last of the real "legacy" models remaining) because it doesn't have these habits as bad.

[felix089]

It's similar for me, it generates so much content without me asking. if I just ask for feedback or proofreading smth it just tends to regenerate it in another style. Anything is barely good to go, there's always something it wants to add

[abustamam]

It's also annoying when it starts obsessing over stuff from other chats! Like I know it has a memory of me but geez, I mention that I want to learn more about systems design and now every chat, even recipes, is like "Architect mode - your garlic chicken recipe"

Like, no, stop that! Keep my engineering life separate from my personal life!

[causal]

I'm suspicious it's something far worse: they're increasingly being trained on their own output scraped from the wild.

[dist-epoch]

Because that's where the compute happens, in those "verbose" tokens. A transformer has a size, it can only do so many math operations in one pass. If your problem is hard, you need more passes.

Asking it to be shorter is like doing fewer iteration of numerical integral solving algorithm.

[sambaumann]

Yeah, but all the models live in chatGPT have reasoning (iirc) - they could use reasoning tokens to do the 'compute', and still show the user a succinct response that directly answers the query