[flagged]
Universal Claude.md – cut Claude output tokens
141–150 of 192 posts
Re: Universal Claude.md – cut Claude output tokens
#142[dead]
Re: Universal Claude.md – cut Claude output tokens
#143[dead]
Re: Universal Claude.md – cut Claude output tokens
#144Earlier 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…
Wouldn't the next phase of this be automatic handoffs executed with hooks? Your system is great and I do similar, my problem is I have a bunch of sessions and forget to 'handoff'. The clawbots handle this automatically with journals to save knowledge/memory.
when work on task i have task/{name}.md that write a running log to. is this not a common workflow?
Re: Universal Claude.md – cut Claude output tokens
#145Remember when we worked on new hashing, cryptography, compression, etc algorithms? Now we are trying to find the best ways to tell an AI to be quiet.
Re: Universal Claude.md – cut Claude output tokens
#146[dead]
Re: Universal Claude.md – cut Claude output tokens
#147From the file: "Answer is always line 1. Reasoning comes after, never before." LLMs are autoregressive (filling in the completion of what came before), so you'd better have thinking mode on or the "reasoning" is pure confirmation bias seeded by the answer that gets locked in via the first output tokens.
Is this true? Non-reasoning LLMs are autoregressive. Reasoning LLMs can emit thousands of reasoning tokens before "line 1" where they write the answer.
reasoning is just more tokens that come out first wrapped in
Re: Universal Claude.md – cut Claude output tokens
#148Re: Universal Claude.md – cut Claude output tokens
#149Earlier quoted context omitted.
I was reading through the Claude docs and it was talking about common patterns to preserve context across sessions. One pattern was a "handoff file", which they explained like "have claude save a summary of the current session into a handoff file, start a new session, then tell it to read the file." That sounded like a nice idea, so I made it effortless beyond typing /handoff. The generated docs turned out to be real…
Oh, so the word 'gate' is probably in the documentation also! I see. So this isn't as scary. Claude is helping me understand how to use it properly.
I have noticed similar phenomena with Claude, where its vocabulary subtly shifts how I think/frame/write about things or points me to subtle gaps in my own understanding. And I also usually come around to understand that it's often not arbitrary. But I do think some confirmation bias is at play: when it tries to shift me into the wrong directions repeatedly, I learn how to make it stop doing that.
It definitely adds a layer of cognitive load, in wrangling/shepherding/accomodating/accepting the unpredictable personalities and stochastic behaviors of the agents. It has strong default behaviors for certain small tasks, and where humans would eventually habituate prescribed procedures/requirements, the LLM's never really internalize my preferences. In that way, they are more like contractors than employees.
Re: Universal Claude.md – cut Claude output tokens
#150Is there a "universal AGENTS.md" for minimal code & documentation outputs? I find all coding agents to be verbose, even with explicit instructions to reduce verbosity.
I think this is a fundamental LLM issue. I recall a paper a ways back about trying to get the LLMs to be too succinct, and the problem is, with the way they are implemented, the only way they can "think" is to emit a token. IIRC it demonstrated that even when the model is just babbling something like "Yeah, let's take a look at the issue you just raised" that under the hood, even though that output was superficially useless, it was also changing its state in ways related to solving the problem and not just outputting that superficially useless text.
It helps to understand that, because then you can also not be annoyed by things like "Let's do X. No, wait, X has this problem, let's do Y instead." You might think to yourself, if X was a bad idea, couldn't it have considered X and rejected it without outputting a token?" and the answer is, that sentence was it considering X and rejecting it, and no, there is no way for it to do that and not emit tokens. Thinking is inextricably tied to output for LLMs.
There is even some fairly substantial evidence from a couple of different angles that the thinking output is only somewhat loosely correlated to what the model is "actually" doing.
Token efficiency is an interesting question to ponder and it is something to worry about that the providers have incentives to be flabby with their tokens when you're paying per token, but the question is certainly not as easy as just trying to get the models to be "more succinct" in general.
I often discuss a "next gen" AI architecture after LLMs and I anticipate one of the differences it will have is the ability to think without also having to output anything. LLMs are really nifty but they store too much of their "state" in their own output. As a human being, while I find like many other people that if I'm doing deep thinking on a topic it helps to write stuff down, it certainly isn't necessary for me to continuously output things in order to think about things, and if anything I'm on the "absent minded"/"scatterbrained" side... if I'm storing a lot of my state in my output for the past couple of hours then it sure isn't terribly accessible to my conscious mind when I do things like open the pantry door only to totally forget the reason I had for opening it between having that reason and walking to the pantry.