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

221–230 of 433 posts

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

#221

Post by mips_avatar »

a_c wrote: post #73
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…

Every subagent send the same ~30k system prompts. If you are using fable/opus, that's easily 30% of a 5-hour window for 7 subagent, before doing any work

The shared prompts are all cached so it's a cache read which is like 10x cheaper than a regular prefill

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

#222

Post by neya »

I used both with Openrouter and GLM 5.2 and I can confirm this is the case. Claude Code burned $10 per task while Open Code burned barely $10 a day which wqs about 4-5 tasks a day. A task usually included database migrations, code audit or documentation.

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

#223

Post by GodelNumbering »

It is not the raw prompt size that matters ultimately, otherwise Pi (and variants) would be the lowest costing agents. What matters is how efficient the prompt it. Prompt minimalism often gets conflated with efficiency. Having said that, CC does seem bloated for what it does.

What matters even more is tooling quality. Bad/buggy tooling causes a lot more roundtrips that wipes out all gains from initial greedy approach.

A few months ago, I did a full benchmark run of 7 agents over 8 tasks (https://github.com/dirac-run/dirac has the data and traces). I cannot claim neutrality because of the obvious connection to one of those, but the data should be reproducible and useful. Importantly, Dirac wins there significantly on those tasks because they are mostly refactoring related (which is where approaches like hash-anchoring and AST parsing tend to shine)

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

#224

Post by brianwawok »

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…

lol I asked fable to help me estimate my TAM and it launched 102 agents and blew my $120 quota in 6 minutes. I do realize I can limit the agent count , hah

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

#225

Post by hoppp »

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.

I think I use it differently. I still mainly stick to web UI.

I write a good prompt, paste the code then copy the output code and place it into my project.

So in the end I hand assemble and I only give it what it needs to know so no extra context wasted.

The human in the loop is of course the secret sauce but this way I am highly efficient, no vibecode and I work really fast too. Everything is audited.

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

#226

Post by azinman2 »

prjkt wrote: post #214
azinman2 wrote: post #211

Earlier quoted context omitted.

If I were anthropic I’d force that too. They offer the harness and if they control the entire pipeline then they can optimize the entire experience. It doesn’t have to be nefarious.

It's like Microsoft banning Vim users that use Azure

It’s really not. Vim isn’t instrumental to Azure usage.

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

#227

Post by twelve40 »

drob518 wrote: post #205
leptons wrote: post #135

Earlier quoted context omitted.

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.

Of course it is. How could it be anything different? Clearly, that’s how these companies make money.

it's a very handwavey way to "explain" anything. Yes, they make money. But they have competition. And if someone runs out of tokens and switches to deepseek or just goes for a friggin hike in the woods, that does not benefit them. If they get a public image of a ripoff that burns all shit on trivial tasks, that does not do them good either. So there is a limit to this "companies make money" thing.

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

#228

Post by hoppp »

giovannibonetti wrote: post #187
ACCount37 wrote: post #159

Earlier quoted context omitted.

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 cour…

Perhaps what is missing is a better memory/caching layer to avoid doing the same for explorations over and over again.

I use the human-in-the-loop for managing the context.

Give it only what it needs and do things usually 1 file at a time.

Feels like I'm a sort of manual tape editor, if the context was a tape fed into machine, I assemble that and then watch the machine output the results I need.

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

#229

Post by ejpir »

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.

what tools are you talking about? Pi has ALL tools the LLM needs to function efficiently and effectively for coding tasks. It can read,write,edit files and can use any bash tool to search files, execute tests and so on.

Every time I read this comments I have the feeling you are talking about mcp or sub agents, otherwise this makes no sense at all.

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

#230

Post by dpritchett »

giovannibonetti wrote: post #187
ACCount37 wrote: post #159

Earlier quoted context omitted.

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 cour…

Perhaps what is missing is a better memory/caching layer to avoid doing the same for explorations over and over again.

That is the usual work of high end programmers, right? Growing codebases as consistent, dependable ontologies?

I feel like most mainstream programming languages do this sort of work for their standard libraries and their official docs. Go and Python come to mind, but plenty others do this reasonably well to the point where one mostly doesn’t need to read the implementation code to effectively use the standard library itself.

Post reply on HN