Earlier quoted context omitted.
tokens definitely measure compute.
You can ask it to verbatim produce training data and that takes very little compute for a lot of output tokens
i dont think you understand how these models operate.
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
401–410 of 433 posts
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#402Its funny, I have seen people look at the sourcecode of opencode and complain about excessive token use, the code to tell the model how to execute bash commands, and they complained how this was way too excessive, teaching the LLM how to write bash.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#403Earlier quoted context omitted.
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.
Depends on if they are launched serially or in parallel then.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#404Noob question, but is there, on a harness level, a way to compress or optimize the "pre processing prompt" or any other preamble?
I know you can give instructions to guide an agent, but they are still plain English, the interpretation still isn't absolute and the more rules, the less likely it is to respect the whole set of rules in the preamble, but the whole process seem so... "Unprofessional"?
As I see it, a tool should be reliable and the less bloat, less possible points of failure.LLMs seem overly verbose and you can't shake the feeling it might veer away from the objective at any point. You can pay to mitigate or work around the risk, but it still doesn't inspire confidence in anything with more than 30 lines
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#405Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#406Earlier quoted context omitted.
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.
It's the same conflict of interest quite literally any business has. What stops any business from over-charging? Competition.
> What stops any business from over-charging? Competition.
I fully agree.
> It's the same conflict of interest quite literally any business has.
I know that you know what I meant ;) In the long term it is just as you say - overcharging (eventually corrected by competition forces), but in the short term it can be additional revenue, blamed on a bug, but making some manager look good.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#407Earlier quoted context omitted.
Bloated TUI library, unified multi-provider LLM layer, bloated RPC and SDK modes, the entire plugin framework, the list goes on and on. For reference, pi-coding-agent, by itself (not including dependencies, tests, or pi-ai, pi-tui, pi-agent-core, etc), is ~41,653 SLOC taking up ~1658.9 KiB across 163 files. My agent, excluding dependencies (all go stdlib) and tests, is 3 files, 946 SLOC, taking up 36.3 KiB, and inclu…
Sure, if your fundamental issue is “bloat,” you can always write a less general-purpose system that is smaller. No doubt about that.
I guess better phrasing would be auditability, ease of codebase comprehension, coverage of just the features I want. My agent isn't meant to be for X users across Y providers with Z extensible plugins, it's meant for exactly one user, with exactly one provider, and to minimize the amount of trust granted to third parties.
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#408What 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
[flagged]
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#409What 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
[flagged]
Re: Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
#410Earlier quoted context omitted.
You can ask it to verbatim produce training data and that takes very little compute for a lot of output tokens
i dont think you understand how these models operate.
You can burn kilowatts generating 10 tokens, and conversely produce millions of tokens burning very few watts. You're comment is horse shit