Vomit: Clean up Claude 5's token output with a separate LLM

Post by roarcher » Fri, Aug 21, 2026, 5:59 AM UTC

throwaway894345 wrote: post #208

cnity wrote: post #204

Earlier quoted context omitted.

I've noticed that most people seem to consider the core problem of Claude's output as "too verbose" but I don't think this actually cuts to the heart of the matter at all. It's almost, in some weird way, the opposite: like the text is far too _dense_. It tries too hard to invent odd terminology to try to condense stuff, but it doesn't tell you up front that it is going to call your company wide error-handling mechani…

Kind of both. On the one hand, it is “verbose” in the sense that it will tell me every little nit that it can think of while doing a task, it will tell me a narrative about its thought process, and it will tell me every other detail it can think of. But it does so in a way that tries to be incredibly dense to the point that I have to struggle to figure out what it is saying. I wonder if there are any “legibility benc…

Post by ivankabiden » Fri, Aug 21, 2026, 6:41 AM UTC

juancn wrote: post #28

Just set the following incantation: You must use ASD-STE100 Simplified Technical English (STE) when it doesn't detract from meaning.

Post by manmal » Fri, Aug 21, 2026, 6:53 AM UTC

striking wrote: post #214

throwaway894345 wrote: post #208

Earlier quoted context omitted.

Kind of both. On the one hand, it is “verbose” in the sense that it will tell me every little nit that it can think of while doing a task, it will tell me a narrative about its thought process, and it will tell me every other detail it can think of. But it does so in a way that tries to be incredibly dense to the point that I have to struggle to figure out what it is saying. I wonder if there are any “legibility benc…

I quite like https://surgehq.ai/benchmarks/hemingway-bench

Post by JacobAsmuth » Fri, Aug 21, 2026, 7:11 AM UTC

brokencode wrote: post #167

qwerpy wrote: post #89

Earlier quoted context omitted.

HN's mood is usually sour about everything, but can be temporarily influenced by emotionally-charged (usually political) events. The anti-US administration boost wore off and now we're back to being sour about Anthropic. It's time for Dario to tweet something antagonistic towards the administration or endorse some fashionable political candidates.

When were they ever anti-administration? I only remember them being anti- killer AI and mass surveillance.

Post by Bluestein » Fri, Aug 21, 2026, 7:12 AM UTC

qlte wrote: post #124

bcooke wrote: post #51

Earlier quoted context omitted.

Very well said. And when you say it like that, I have to wonder how much of this is a natural consequence of RHLF on such a grand scale, when you have millions of people pretty much much skimming chat responses or operating outside their depth and giving unqualified feedback to the models. Seems like a lot of people may be reinforcing what sounds smart over what is smart. Also as an aside: funny how much the LLMs con…

I believe we are several generations past peak-RLHF at this point. Now it's much more RLVR (Reinforcement Learning with Verifiable Rewards), with a goal/evaluator loop. Which, conveniently, fits neatly into the benchmaxxing arms race/agentic coding market fit, since you can basically train "directly" on a specific problem space for a benchmark/agentic goal (fudged sufficiently to avoid excess overfitting on public pr…