Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

systima.ai

Post reply on HN
Print view View original

31–40 of 433 posts

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#32

Post by arcanemachiner »

mft_ wrote: post #11
bel8 wrote: post #6

And pi agent is even less. The entire agent system prompt can be seen here: https://github.com/earendil-works/pi/blob/main/packages%2Fco...

Maybe related to this minimalism, Pi doesn't come with most of the tools an LLM needs to function efficiently or effectively. I get that a blank slate is the paradigm, and you can add whatever you want, but it's too blank IMO.

I have a functional Pi config, mostly self-made (it has everything I want, incl. subagents, web search, a /btw command, and other misc. addons), and my system prompt is ~3k.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#33

Post by alex7o »

tyleo wrote: post #19
alex7o wrote: post #13

I am forced to use cloude code at work but a good solution is to just use --system-prompt "" and be done with it. I wish they allowed for other harnesses.

I didn’t know you could do this. Is there any analysis of the impact, before and after? I’d love to see some charts of efficacy in real world usage.

It shows up in /context, but never spend time validating it much. Some people run a proxy to modify their messages.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#35

Post by mh- »

prymitive wrote: post #18
jakozaur wrote: post #5

This isn’t limited to large system prompts. Coding-agent harnesses are also becoming more aggressive about using tools, even for trivial requests. In our tests, prompts such as “Hey” or “commit” sometimes triggered 30+ tool calls: https://quesma.com/blog/the-true-cost-of-saying-hi-to-an-ai-... Tokenflation seems very real: the number of tokens consumed by simple tasks keeps increasing.

I often find myself annoyed when Opus fixes a typo in a comment and decides to run tests, lints and whenever else it can find to run. Often it will start by stashing current changes just to preemptively check if all tests were passing before. And I can blame myself a bit because my rules do say: verify all changes with tests. But as there is that I in AI that is hyped which you’d think means it knows not to put tomat…

> [..] my rules do say: verify all changes with tests

I am a bit surprised that you're disappointed that it does exactly what you told it to - people usually have the opposite complaint.

If you're using it interactively and watching what it changes, I'd trigger the tests when you think it's needed. And if you want to go more hands-off, why not add try to encode the same nuance you'd use into the rule?

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#36

Post by wolttam »

docheinestages wrote: post #20

I've been trying various harnesses like Pi, OpenCode, Qwen Code, and Nanocoder. A common problem I keep running into is failed tool calls, regardless of the model. What is the best harness and on-device model combination right now?

> and on-device model combination right now

That would depend entirely on what your device is. This sounds likely not to be an issue with the harness, but the capabilities of the models you've tried.

I experience almost no tool call failure using my nothing-special harness and DSv4 Flash.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#38

Post by toddmorey »

korrectional wrote: post #26

My opinion is that claude code uses more tokens simply because Anthropic makes more money that way and forces people into their subscriptions. This is supported by the fact that they won't let you use your sub on a different coding agent. I use pi btw.

I thought I read somewhere that according to filings for going public, subscription revenue is tiny… like 5%.

Edit: consumer Claude subs are the 5%. I’d bet most all of CC subs lump in under enterprise.

  - API & Enterprise: 75% to 85% of total revenue.
  - Business Subscriptions: Roughly 10% to 15%.
  - Individual Subscriptions: About 5%.

Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k

#39

Post by systima »

PUSH_AX wrote: post #34

This is like saying contractor (A) asked for $33,000 to undertake the work and contractor (B) asked for $7,000 Are we measuring and caring about the right thing?

Anecdotally, the results from OpenCode + Claude appear to be the same if not better for our uses over the past year.
Post reply on HN