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

271–280 of 433 posts

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

#271

Post by stingraycharles »

Schiendelman wrote: post #98
estetlinus wrote: post #48

Recently switched to Codex after 6m in Claude. Codex seems more open, it’s easier to follow what the model is doing and the approvals have a better UX. Overall, it just feels more transparent. Cost of switching was close to 0. I don’t like that Claude became more opaque around February, including the system prompts. 33k feels way too much.

What settings have you tried since it "became more opaque"? They've got a lot more settings now.

They’ve been hiding their thinking tokens more and more, and lately also which tools are being executed when and in which way. It makes it more difficult to assess what it’s doing and jump in to steer it into a different direction in realtime.

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

#272

Post by xpct »

leptons wrote: post #135
mcv wrote: post #53

What really burns tokens is sub agents. I once gave Claude Code a pretty big task, and it immediately launched 7 sub agents which burned through my budget before even one of them was finished. Tried again 5 hours later: same result. If I let the main agent do the same task sequentially, it was no problem at all. I don't know if it's really just communication and orchestration that makes sub agents so inefficient, or…

It's in the best interest for AI companies to gobble up tokens. I feel like every new release - Fable, etc - is just a way to extract more tokens/money.

(If) something like the current LLM/agent paradigm remains in a few years, and companies settle down into their respective niches, I imagine more user-friendly tools will be built, with more control over subagent spawning, context, caching, etc.

What's happening this year, with secrecy and all, is saddening, but expected.

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

#273

Post by marcus_holmes »

I've been trying out OpenCode recently, because of the US embargo on frontier models, and found it to be as good as Claude Code, if not better. And it read all my skills, claude.md files, etc. Now I just need to pick a model out of all the choices - currently Deepseek v4 Pro is winning, but I want to try a few more.

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

#275

Post by pohl »

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.

It starts lean, yeah. Did you know you can prompt it to add the capability you feel you’re missing?

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

#276

Post by ls612 »

drob518 wrote: post #199
mcv wrote: post #193

Earlier quoted context omitted.

Fable and sub agents are two different things. There are many situations for which Fable is great, but Fable doesn't have to run in a sub agent. You can use it for your main agent and that works fine. Or are you saying my sub agents burned so many tokens because they were all using Fable, whereas my main agent could do the same job with a lesser model?

I think the commenter (who is not me) is saying to use Fable as the main agent but then use lesser models for your subagents so that you get the advantages of Fable to plan but then the subagents don’t cost as much, and may be more focused because they lack Fable’s thinking modes.

I’ve heard the proper pattern is to have Fable write a software design doc and then tell Opus to follow that doc strictly in implementation and testing.

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

#277

Post by AdieuToLogic »

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 use pi btw.

When using Pi, one way to significantly reduce input tokens it yields is to ignore common bookkeeping "dot directories", such as `.git`. How to do so can be found with the following interactive Pi prompt:

  How do I configure Pi to ignore git related artifacts, such 
  as the project's .git directory?
Other local assets to consider ignoring are `.pi`, `.agents`, `*.md`, and language specific output directories such as `__pycache__`, `bin`, `obj`, `target`, etc.

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

#278

Post by maxgashkov »

paxys wrote: post #54
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.

You're making the opposite argument. Anthropic is incentivized to use less tokens in Claude Code because people are paying a fixed monthly fee for subscriptions.

Not really. The incentive is to make you hooked on the process, so you bring the same process to the workplace, and start paying corporate prices, not individual subscription prices. For that to work Claude Code, prompt, and the rest of the mechanics has to be more or less uniform.

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

#279

Post by RussianCow »

ricardobeat wrote: post #134
micw wrote: post #81

Earlier quoted context omitted.

I recently did a few tests. And always the same prompt has been cached properly.

Cache is usually not shared between agents - they can have different base prompts, tools, and be an entirely different model.

Compared to the primary agent, maybe. But it's highly unlikely that all the agents have different tools and system prompts than each other, and those account for the bulk of the context per the post.

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

#280

Post by shepherdjerred »

systima wrote: post #79

UPDATE: After reading PUSH_AX's valid comment: ``` 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? ``` We will update the post to include: 1) A more in-depth task. 2) Qualitative results comparison. 3) As soon as possible, a reproduction of the inputs and outputs.

If cost were the only factor of course you'd use B, but presumably you also care about quality quite a bit.
Post reply on HN