alt Hacker NewsIt 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's writing massive files, allow the session to remain more coherent and focused as context size grows? And in doing so, does it save overall tokens by making better, more grounded decisions?
The original link here has one rule that says: "No redundant context. Do not repeat information already established in the session." To me, I want more of that. That's goal-oriented quasi-reasoning tokens that I do want it to emit, visualize, and use, that very possibly keep it from getting "lost in the sauce."
By all means, use this in environments where output tokens are expensive, and you're processing lots of data in parallel. But I'm not sure there's good data on this approach being effective for agentic coding.
Replies
Seems crazy to me people aren't already including rules to prevent useless language in their system/project lvl CLAUDE.md.
As far as redundancy...it's quite useful according to recent research. Pulled from Gemini 3.1 "two main paradigms: generating redundant reasoning paths (self-consistency) and aggregating outputs from redundant models (ensembling)." Both have fresh papers written about their benefits.
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.
> No explaining what you are about to do. Just do it.
Came here for the same reason.
I can't calculate how many times this exact section of Claude output let me know that it was doing the wrong thing so I could abort and refine my prompt.
I made a test [0] which runs several different configurations against coding tasks from easy to hard. There is a test which it has to pass. Because of temperature, the number of tokens per one shot vary widely with all the different configurations include this one. However, across 30 tests, this does perform worse.
if the model gets dumber as its context window is filled, any way of compressing the context in a lossless fashion should give a multiplicative gain in the 50% METR horizon on your tasks as you'll simply get more done before the collapse. (at least in the spherical cow^Wtask model, anyway.)
[dead]
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 coherency, but my sessions do occasionally reference those docs. More than that, it’s an excellent “daily report” type system where you can give visibility to your manager (and your future self) on what you did and why.
Point being, it might be better to distill that long term cohesion into a verbose markdown file, so that you and your future sessions can read it as needed. A lot of the context is trying stuff and figuring out the problem to solve, which can be documented much more concisely than wanting it to fill up your context window.
EDIT: Someone asked for installation steps, so I posted it here: https://news.ycombinator.com/item?id=47581936