351–360 of 433 posts
Is that true? My understanding is that the subagent only returns the result of the request without the main agent consuming its entire transcript.
Earlier quoted context omitted.
> 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. Probably because the general purpose subagents inherit the parent model. I tell Claude explicitly to use Explore subagents, which use Haiku only, now.
They changed it with the release on July 1 Explore now inherits the model, it isn't always haiku. https://code.claude.com/docs/en/changelog#2-1-198 > The built-in Explore agent now inherits the main session’s model (capped at opus) instead of running on haiku
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.
Therefore, you should include the actual costs associated with the task in API token usage or subscription level. Is there a reasonable way to do apples to apples cost comparison?
Wouldn't be surprised if you're paying full price for those tokens, but they cost ~$0 for the provider.
Earlier quoted context omitted.
Everything about LLMs is inefficient. They have their benefits but watching them reason over things that are painfully obvious, that they've literally investigated before (before a memory compaction), never take a step back aand be like 'this is going too slow let me look for a better way', etc. is painful.
It’s got worse though right? Older models from before everyone went off the deep end with CoT don’t do this and just write the code with 1/10 the token usage. The downside is the code isn’t as good but it is produced a lot faster and more cheaply and often it’s actually fine. CoT has made LLMs better (say 50% improvement or something) but increases cost by an order of magnitude. That graph is going in the wrong direc…
Earlier quoted context omitted.
It’s got worse though right? Older models from before everyone went off the deep end with CoT don’t do this and just write the code with 1/10 the token usage. The downside is the code isn’t as good but it is produced a lot faster and more cheaply and often it’s actually fine. CoT has made LLMs better (say 50% improvement or something) but increases cost by an order of magnitude. That graph is going in the wrong direc…
CoT?
Earlier quoted context omitted.
I'd like to understand what features you're referring to that are missing from base-install Pi CLI.
The main ones missed immediately were web access/search. Then the to-do list features (it was a nice surprise to try OpenCode and see this working immediately.). There were a couple of other niggles but it was a few months ago. Also, this may not be common, but it seemed to struggle to edit effectively (driven by Qwen 3.6 35b/27b) and often rewrote whole files instead.
Though, imo, the fact that pi maintains its "we only include the bare minimum!" statement is part of the draw for me. Especially considering that im in an enterprise env; being able to internally share custom implementations of out-of-the-box Codex/CC stuff is really nice.
I do wonder how they'd go about shipping a default web search tool. Big problem there is the lethal trifecta. Shipping something that arbitrarily allows untrusted content to be retrieved non-deterministically I'm sure is a long conversation on Pi's end. Pushing it off to the user to decide is easy.
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.
This isn't accurate since the main reason I'm using Claude Code instead of these other interesting sounding harnesses is the subscription service with highly discounted token usage. With OpenCode, you're paying the full price. Therefore, you should include the actual costs associated with the task in API token usage or subscription level. Is there a reasonable way to do apples to apples cost comparison?
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…
They optimized it to burn more token in the recent months I feel. I made a small ~100 line change to a codebase by hand and threw claude at it to review. It spawned several sub-agents and burnt a ton of tokens. I guess the word 'review' now triggers some sort of in-built skill or something. It's absurd how rapid enshittification is taking over.
But somehow the cost has doubled in the last few months.
Earlier quoted context omitted.
Oh-my-pi has more tools than claude and opencode, and uses them much more efficiently. my favorites are /collab and the gortex mcp
I tried using omp, and really like the interface, but I found it used tokens much much quicker than the Claude cli. Some simple tasks would use all the session tokens in less than an hour, as where I could get easily get 3-4 hours with Claude. Both set to use opus 4.8 auto effort. I tried tweaking the models for agents down to haiku and sonnet in omp, but didn't notice any real difference in the speed tokens were bei…