Earlier quoted context omitted.
Certainly load bearing, great call.
Importantly, blast radius is confirmed and systemic gaps safely sealed.
A caveat though, and it's a real one: Not all seams have been.-
Vomit: Clean up Claude 5's token output with a separate LLM
251–260 of 315 posts
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#252[dead]
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#253[flagged]
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#254Apposite name but — grim trivia — bear in mind some emetophobes have a meaningful physiological reaction to the word and various euphemisms. I have tried not to use it analogously ever since someone pointed this out. The word itself causes discomfort for a lot of people, many of whom will be surprised by it out of context, but in a non-trivial fraction it causes proper discomfort. If you want people to use your tool…
I am feeling nauseous and I dind't even think that it might have been due to what I was reading. Nice info, thanks.
I only realised when I was told about it that, while for me it doesn't have that nausea trigger, it does have a bit more alert associated with it — which is probably why I made my comment at all. I am not emetophobic (might have risen to that level as a child).
But having an awareness of that alert feeling is a very useful mental model for how some other words or phrases may cause a heightened response with different parts of an audience; it is a useful caution.
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#255I've been grappling with this for weeks, not just in Claude but in Codex as well, which isn't quite as bad but still annoying. AGENTS.md does very little, agents will consistently violate the communication preferences, especially as the session drags on. It's incredible to me that there's no good way to reliably change the way an LLM responds to you that a workaround like this would even be necessary. It seems like s…
I'm probably going to be going against the grain here, but I think it's not as bad as it looks at first. I was similarly frustrated a few months ago, but have noticed I've started to learn the idiom. Its use of "dense jargon" and "stilted metaphor" is actually surprisingly consistent - it's speaking its own dialect, and you get used to it. After a while it gets much easier to read and even becomes somewhat efficient,…
You can get used to it and it still be rage inducing.
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#256Re: Vomit: Clean up Claude 5's token output with a separate LLM
#257I am actually fine-tuning a version of Qwen to re-write Claude slop. This will complement it nicely
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#258They just released an update to handle this. ouputStyle: concise https://x.com/claudedevs/status/2090245922685063634?s=46&t=Z...
The amazing "solution" is basically telling the model to STFU every single turn. I guess this works better than putting it just in the claude MD since then it's never out of context.
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#259Earlier quoted context omitted.
Claude is the Deepak Chopra of computer programming. Reviewing PR's created by it is 90% digesting the meaningless word salads in the comments, and the rest is figuring out that it has nothing to do with the code it is commenting.
Because it is somehow incapable of separating the conversation with its human operator from the code it is generating and commenting on. Incidentally, this is also why prompt-injection works. No one wants to know about the three other approaches tried when reading the first sentence of a function's documentation. No one cares that the implementation was planned in six phases and "Phase 3" will implement this interfac…
And worse yet, you'll find the code peppered with comments relating to 'phase 3' and 'section 11', ephemeral stuff that had meaning in the moment but now enshrined forever. And what happens when the LLM stumbles on this and working off a whole different phase 3 or section 11?
Re: Vomit: Clean up Claude 5's token output with a separate LLM
#260Can't wait for tomorrow's HN front page so we can learn about the 5 additional AI tools needed to make this work properly. And then the day after, each of those will require more agentic tools to manage the agents that manage the agents that manage the agents. Then you need to install Flooper to stop Wigwam from too aggressively rebooting the Glupgo instance that's in charge of making sure your credit card informatio…
[dead]