Earlier quoted context omitted.
Why would it be scary? Claude is just parroting other human knowledge. It has no goal or agency.
By that logic, nothing computers do is scary.
Yes I think that is their argument.
Universal Claude.md – cut Claude output tokens
111–120 of 192 posts
Re: Universal Claude.md – cut Claude output tokens
#112Does Claude not respect AGENTS.md? I love how seamless and intuitive Codex is in comparison: ~/AGENTS.md Meanwhile Claude doesn't even see that I asked for indentation by tabs and not spaces or that the entire project uses tabs, but Claude still generates codes with spaces.. >_<
It needs to be called CLAUDE.md for Claude Code
Re: Universal Claude.md – cut Claude output tokens
#113Earlier quoted context omitted.
I wrote a skill called /handoff. Whenever a session is nearing a compaction limit or has served its usefulness, it generates and commits a markdown file explaining everything it did or talked about. It’s called /handoff because you do it before a compaction. (“Isn’t that what compaction is for?” Yes, but those go away. This is like a permanent record of compacted sessions.) I don’t know if it helps maintain long term…
Did you call it '/handoff' or did Claude name it that? The reason I'm asking is because I noticed a pattern with Claude subtly influencing me. For example, the first time I heard the the word 'gate' was from Claude and 1 week later I hear it everywhere including on Hacker News. I didn't use the word 'handoff' but Claude creates handoff files also [0]. I was thinking about this all day. Because Claude didn't just use…
I've started saying "gate" and "bound(ed)" and "handoff" a lot (and even "seam" and "key off" sometimes) since Codex keeps using the terms. They're useful, no doubt, but AI definitely seems to prefer using them.
Re: Universal Claude.md – cut Claude output tokens
#114Does Claude not respect AGENTS.md? I love how seamless and intuitive Codex is in comparison: ~/AGENTS.md Meanwhile Claude doesn't even see that I asked for indentation by tabs and not spaces or that the entire project uses tabs, but Claude still generates codes with spaces.. >_<
It needs to be called CLAUDE.md for Claude Code
Oh my god, why
Why do they have to have that "I'm special" syndrome and do everything weirdly
Re: Universal Claude.md – cut Claude output tokens
#115Earlier quoted context omitted.
Is this available online? I'd love documentation of my prompts.
I’ll post it here, one minute. Ok, here you go: https://gist.github.com/shawwn/56d9f2e3f8f662825c977e6e5d0bf... Installation steps: - In your project, download https://gist.github.com/shawwn/56d9f2e3f8f662825c977e6e5d0bf... into .claude/commands/handoff.md - In your project's CLAUDE.md file, put "Read `docs/agents/handoff/*.md` for context." Usage: - Whenever you've finished a feature, done a coherent "thing", or oth…
I already do this manually each time I finish some work/investigation (I literally just say
"write a summary handoff md in ./planning for a fresh convo"
and it's generally good enough), but maybe a skill like you've done would save some typing, hmm
My ./planning directory is getting pretty big, though!
Re: Universal Claude.md – cut Claude output tokens
#116I told mine to remove all unnecessary words from a sentence and talk like caveman, which should result in another 50% savings ;)
Memory unlocked: https://www.youtube.com/watch?v=_K-L9uhsBLM
Re: Universal Claude.md – cut Claude output tokens
#117In Claude Code's /usage it just hangs. I can't even see what my limits are, which is weird. Maybe a bug? I can't imagine I'm close to my limits though, I'm on Max 20x plan, using Opus 4.6.
Re: Universal Claude.md – cut Claude output tokens
#118So many problems with this: The benchmark is totally useless. It measures single prompts, and only compares output tokens with no regard for accuracy. I could obliterate this benchmark with the prompt "Always answer with one word" This line: "If a user corrects a factual claim: accept it as ground truth for the entire session. Never re-assert the original claim." You're totally destroying any chance of getting pushba…
“Make no mistakes”
Re: Universal Claude.md – cut Claude output tokens
#119It seems the benchmarks here are heavily biased towards single-shot explanatory tasks, not agentic loops where code is generated: https://github.com/drona23/claude-token-efficient/blob/main/... And I think this raises a really important question. When you're deep into a project that's iterating on a live codebase, does Claude's default verbosity, where it's allowed to expound on why it's doing what it's doing when it…
also: inference time scaling. Generating more tokens when getting to an answer helps produce better answers. Not all extra tokens help, but optimizing for minimal length when the model was RL'd on task performance seems detrimental.
I liked playing with the completion models (davinci 2/3). It was a challenge to arrange a scenario for it to complete in a way that gave me the information I wanted.
That was how I realized why the chat interfaces like to start with all that seemingly unnecessary/redundant text.
It basically seeds a document/dialogue for it to complete, so if you make it start out terse, then it will be less likely to get the right nuance for the rest of the inference.