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

261–270 of 433 posts

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

#261

Post by blitzar »

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've done a couple side by sides on web chat with the same prompt on local 4b, 14b, 32b open models and the output gets longer/more verbose on version increment.

Its rather frustrating, slower tokens and more tokens.

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

#263

Post by blitzar »

shric wrote: post #259
blitzar wrote: post #258

Sending 0k tokens would be a smaller number again. But then it might have no idea of what it is doing. I pay my subscription and get lots of tokens on good models - if I was paying per token I might care more. In a pay per token situation, there is a huge conflict of interest with the harness provider and the token seller being the same party ... efficiency is less profitable. I have accused claude code of trying to…

> In a pay per token situation, there is a huge conflict of interest with the harness provider and the token seller being the same party ... efficiency is less profitable. Except there’s a competitive incentive to either use less tokens or make the tokens go further

We are still in a (brief) era where companies are awarding pizza parties to the employees that burn the most tokens.

There is a world where, to hit the next quarters revenue projection, you add 2,000 tokens to the system prompt and "beat" expectations at the next earnings release.

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

#264

Post by hoppp »

jumpkick wrote: post #233
hoppp wrote: post #225

Earlier quoted context omitted.

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.

This is how I worked with LLMs originally, and I much preferred it. This gave me a much better understanding of the code that I was adding. But, there's no way to keep up with my team like this anymore. It's just too slow when everyone else is working directly in Claude Code.

If the entire team is vibe coding and there is no human audit then there is no way but to vibe code, for sure.

I would also just vibe it if there is no responsibility, but if I do it that way I don't even care what happens with the project.

I get so detached from it that I stop caring and if it has huge critical bugs..I just don't care anymore because it's not my responsibility or my code at all at that point. I'm just there to nudge things along.

Just hook it up to Jira and let the managers add the features then pass it off to QA.

Real engineering is fully automated at that point.

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

#265

Post by avinoth »

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…

I’ve had similar experiences. I now have an explicit line in AGENTS.md to not use subagents unless explicitly requested. It also helps that for the tasks that are big enough to benefit from subagents are also the ones with high chances of going off-rails and/or a poor review phase. I’d rather do the orchestrator role and that way I can split up the review phase in a much more manageable chunk.

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

#266

Post by smrtinsert »

roncesvalles wrote: post #169

I still think the best way to build software using LLMs is to copy-paste snippets/files into the chat and manually guide the work. Humans are still the best orchestrators. Yes the human has to now be hyper-focused and juggle various workflows, but the end result (quality of work and throughput of usable code) becomes very good.

Been my experience as well. Human corrected code is orders better than ai generated slop. Slop might get you the promotion at your day job who is still in fomo tokenmaxx mode, but highly recommend the careful review for your personal projects

I find it hilarious people think they can build on slop or on captured output from quality engineers. Intent is the most important aspect, and no code base could ever capture that

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

#267

Post by anonym29 »

drob518 wrote: post #212
anonym29 wrote: post #10

Earlier quoted context omitted.

If you really want a minimal agent that you heavily customize, just skip pi (130+ transitive dependencies on the "minimal" pi-coder package) and write your own. You learn a bunch, and it's not hard. You can even ask another LLM to help you get started.

That’s certainly doable, but then you need to create all the add-ons you would have added to Pi. IMO, Pi stands in that sweet spot between being very minimal while still offering a catalog of pluggable functionality that you can add to it. Sure, you could vibe code all those things for your custom agent as well, but why recreate what is essentially Pi all over again (the main loop with all the extension hooks, etc.)?…

Pi has way too many batteries included, including a bunch I don't want, and lacked the batteries I did want. Pi is a bit like the movie Idiocracy in that the idea is much better than the execution.

Incidentally, I also have zero supply chain attack surface as I have zero dependencies in my agent, just go stdlib. Pi, again, has 130+ transitive dependencies asking me to trust the security of my system to 150+ additional people I've never met in exchange for a bunch of bloat I do not want.

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

#268

Post by mancerayder »

hoppp wrote: post #225
adastra22 wrote: post #116

Earlier quoted context omitted.

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.

I like it but how much context does it need for a complex program? If you're giving instructions and using its code, I imagine context is being passed back up in an exponential way. If not, and you give it a very thin context every time, how do you manage to prompt it enough?

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

#269

Post by mancerayder »

hoppp wrote: post #264
jumpkick wrote: post #233

Earlier quoted context omitted.

This is how I worked with LLMs originally, and I much preferred it. This gave me a much better understanding of the code that I was adding. But, there's no way to keep up with my team like this anymore. It's just too slow when everyone else is working directly in Claude Code.

If the entire team is vibe coding and there is no human audit then there is no way but to vibe code, for sure. I would also just vibe it if there is no responsibility, but if I do it that way I don't even care what happens with the project. I get so detached from it that I stop caring and if it has huge critical bugs..I just don't care anymore because it's not my responsibility or my code at all at that point. I'm ju…

Are the QA team bearing the brunt of the unexpected issues, bugs, performance etc or is it business-as-usual?

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

#270

Post by vinnymac »

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…

Yesterday I gave Claude Fable a difficult task. It then proceeded to spawn 415 agents. It got it done, but damn was it expensive.
Post reply on HN