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

151–160 of 433 posts

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

#151

Post by crewindream »

lkbm wrote: post #142
claw-el wrote: post #88

Earlier quoted context omitted.

Once I realized that Anthropic is a token merchant, I start to understand Anthropic’s decision more. They are always finding reasons for you to use more tokens through them unless the users revolt or demand some guardrails.

Seems unlikely they'd be this dumb. The way to get us to use more tokens is to make those tokens more useful, not less. Anthropic is full of people (including higher-ups) who know this.

But it is much much simpler to make it consume more tokens.

It’s like that saying “What Andy giveth, Bill taketh away”, but in this case it is one company.

There is definitely a conflict of interest.

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

#152

Post by adaml_623 »

rendx wrote: post #120
onlyrealcuzzo wrote: post #107

Earlier quoted context omitted.

This is why I happily use Codex. I run it basically 24/7 on a ~500k line repo, and only rarely run out of quota before the end of the week. My experience with Claude Code was very good until about 2.5 months ago, and then it suddenly turned unbelievably terrible for me. I have not and will hopefully never look back. I still have PTSD from how ungodly terrible it was that last week of using it.

> I still have PTSD from how ungodly terrible it was Please, for the sake of everyone suffering from actual PTSD: Don't. It's hard enough already for victims to communicate what difficulties they are facing without people watering down terminology like that.

They have Coder PTSD or CPTSD.... Is that a better acronym???

Sorry just teasing.

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

#154

Post by tokioyoyo »

FuckButtons wrote: post #58
paxys wrote: post #54

Earlier quoted context omitted.

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.

Nope, that’s not true, because they want you to pay for the higher subscription bracket.

Generally, companies with >150 people can’t use subs. So yeah, it’s mostly a funnel for devs/small companies to eventually vet for the product and convince their enterprise to use it as well.

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

#155

Post by crewindream »

bpodgursky wrote: post #87
FuckButtons wrote: post #58

Earlier quoted context omitted.

Nope, that’s not true, because they want you to pay for the higher subscription bracket.

If they wanted to play games with sub tiers they would just change the rate limits rather than wasting inference.

Flip side is customer psychology. Choosing a more expensive tier leaves better emotion.

Also i doubt there was jira ticket with “make llm more verbose”, rather ticket with “bug makes llms too verbose” gets prioritised taking revenue impact into account.

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

#157

Post by rurban »

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.

Oh-my-pi has more tools than claude and opencode, and uses them much more efficiently. my favorites are /collab and the gortex mcp

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

#158

Post by alansaber »

xhrpost wrote: post #144
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…

For a while everyone was saying sub agents is how you save tokens, use lower quality models with limited context to do simple parts of the job after a smart planning agent has put it all in place. Is that no longer true or is this just the result of sub agent being used at the wrong time?

No, you can definitely configure low cost search and apply subagents. CC and Codex do not. Not sure if this is to improve the reliability of their subagents, or just a play to increase user consumption.

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

#159

Post by ACCount37 »

adastra22 wrote: post #116
btown wrote: post #76

Earlier quoted context omitted.

As a counterpoint: in a complex project, Fable's "curiosity" may be exactly what you want for an exploration and planning stage - not just for the orchestrator that turns your prompt into different angles with which to explore, but for each subagent whose task is to search the codebase for one of those "angles." If you truly want no stone unturned, letting those subagents spawn their own discoveries, and recursively…

The curiosity is inefficient though. So many times I have to stop the agent and tell it to just fucking write the code and try compiling it. Otherwise it will fill its entire context tracing through the program logic to derive from the code itself whether the thing it is about to do would work. It completely fails to notice it can just… try.

It's tuned for the kinds of tasks where "just try" doesn't get good results.

A major complaint with AI code was that AIs struggle with complex codebases, don't respect existing conventions, reinvent functionality multiple times over, etc. So, newer high end AIs are tuned with the "explore/exploit" dial turned towards "explore".

You could probably get it to do things "quick and dirty" with prompting, but that, of course, requires prompting for it.

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

#160

Post by cmiles74 »

nijave wrote: post #149
claw-el wrote: post #88

Earlier quoted context omitted.

Once I realized that Anthropic is a token merchant, I start to understand Anthropic’s decision more. They are always finding reasons for you to use more tokens through them unless the users revolt or demand some guardrails.

I've done a couple side by sides on web chat with the same prompt on Opus 4.6, 4.7, and 4.8 and the output gets longer/more verbose on version increment. The enerr variants are definitely much wordier. On the other hand, the newer variants also tend to benchmark higher so it's not quite a clean argument of "hey the new version eats more tokens"

I think both things can be true: new models benchmark higher and eat more tokens.
Post reply on HN