Comment by belval
13 hours ago
As a fervent Claude Code user who made the switch to GPT 5.6 Sol over Opus 5 over hard-to-read prose this makes me happy. I love your product but the current models are very hard to work with if you need to do a lot of context switching. Brevity is key.
Brevity means less output tokens, which doesn’t really align with the AI vendors incentives (unless there is a causal relationship with people switching, of course).
Though Claude 5 is not too verbose, it’s more like, full of incomprehensible jargon (even when you’re expert in the domain discussed!)
> Brevity means less output tokens, which doesn’t really align with the AI vendors incentives
Actually, I think Jeavon's Paradox [1] means the opposite. If doing X is $100, you may only use it to do X, but not Y, Z, or W. If doing X is $33, maybe you'll use it for X, Y, Z, and W -- spending 1/3 more than you otherwise would.
Or perhaps not you personally, but maybe you'd be willing to spend $100, but three of your friends find it too expensive. If it's only $33 to accomplish some task, then maybe all four are now spending $33.
[1] https://en.wikipedia.org/wiki/Jevons_paradox
It’s messier for LLMs because you cannot easily compare the cost between runs, outside of benchmarks. Evaluating the value of the output is already extremely hard. But then you add the fact that you don’t know the cost of the output before it is generated. And Anthropic doesn’t share their tokenizers. It’s not as simple as your examples to get a signal that tells you to spend more or less
>Brevity is key
Which is something the providers that are trying to watermark their texts can't afford. Superfluous replies give much more opportunity to further encode this junk information.
This ... is not how this works. The model is not speaking longer to watermark anything.
It's exactly how it works - at least potentially. Lean text is harder to watermark because word choices and meanings are tightly constrained.
Low-entropy text is fluff and filler. It's very easy to synonym-substitute words without changing the message - if there even is one.
2 replies →
Perhaps, but there are certainly now catchphrases and words that can indicate it was written with AI i.e. load-bearing, idempotent, etc. Style and structure are in and of themselves, a fingerprint.
1 reply →
That makes no sense. Watermarking only became a thing in the past month. Claude has been spewing unreadable slop for much longer than that.
I also switched to 5.6 Sol for this very reason. It was so exhausting and cringe to read.
Also a codex user but for me brevity is not it's strong suit. I basically have to give it bigger tasks than I am used to to warrant the time it takes to complete. I feel whatever context the tooling adds can also be problematic
> bigger tasks than I am used to
Do they still get split into commits in sensible ways, for you?
I use beads to create tasks and typically it can hammer out a beads task and then commit under the task id
> Brevity is key.
I've found that models interpret "brevity" as "incomprehensible".
Lets see what they do with Opus first. I didn't find Fable 5.0 prose that bad to read, but improvement is always welcome. It's Opus 5.0 that's atrocious.
It's not really brevity - it's the constant writing tropes. It's like they ready a book on advertising copy and that's the only way they can write. Very tedious. Is Sol much better? I might have to switch to that too!