He is singlehandedly responsible for using up an entire city's worth of power and water this way?
The creator of Claude Code's Claude setup
81–90 of 423 posts
Re: The creator of Claude Code's Claude setup
#82Why stop at 5-10?
Make it 5 billion - 10 billion parallel agents.
PR number go up
Re: The creator of Claude Code's Claude setup
#83This feels like the desperate, look at me! post, which is the exact opposite of Andrej Karpathy's recent tweet[0] about feeling left behind as a programmer, as covered on Hacker News[1]. I guess would want to see how sustainable this 5 parallel AI effort is, and are there demonstrably positive outcomes. There are plenty of "I one-shotted this" examples of something that already (mostly) existed, which are very impres…
I wonder what sort of problems you must have to get this upset about the creator of a particular software telling people how they personally use that software Personally I keep open several tabs of CC but it's not often that more than one or two of them would be running at the same time. It's just to keep particular context around for different parts of the same application since it's quite big (I don't use CC for cr…
> I assume "what sort of problems you must have" was directed at me.
I don't really have any sort of personal problem with Boris' post, if what your inflammatory statement was implying.
I also think it was a fairly good description of his workflow, technically speaking, but also glosses over the actual monetary costs of what he is doing, and also as noted above, doesn't really describe the actual outcomes other than a lot of PRs.
Re: The creator of Claude Code's Claude setup
#84This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…
It's all smokes really. Claude Code is an unreliable piece of software and yet one of the better ones in LLM-Coding. (https://github.com/anthropics/claude-code/issues). That and I highly suspect it's mostly engineers who are working on it instead of LLMs. Google itself with all its resources and engineers can't come up with a half-decent CLI for coding.
Reminder: The guy works for Claude. Claude is over-hyping LLMs. That's like a Jeweler dealer assistant telling you how Gold chains helped his romantic life.
Re: The creator of Claude Code's Claude setup
#85Does anyone know if it’s possible to have “ultrathink” be the default instead of saying it in every prompt?
Put it in CLAUDE.md because that just gets added to the prompt
Ah, thank you! Now I feel like an idiot. I guess I was thinking “ultrathink” was a specially interpreted command within claude code (sort of like a slash command).
Re: The creator of Claude Code's Claude setup
#86Does anyone know if it’s possible to have “ultrathink” be the default instead of saying it in every prompt?
https://x.com/bcherny/status/2007892431031988385?s=20
Seems to be moved to the default now. PSA for anyone who didn't see
Re: The creator of Claude Code's Claude setup
#87This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…
LLM agents can be a bit like slot machines. The more the merrier.
And at least two generate continuous shitposts for their companies Slack.
That said, having one write code and a clean context review it is helpful.
Re: The creator of Claude Code's Claude setup
#88This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…
I usually have 4-5, but it's because they are working on different parts of the codebase, or some I will use as read only to brainstorm
Re: The creator of Claude Code's Claude setup
#89This is interesting to hear, but I don't understand how this workflow actually works. I don't need 10 parallel agents making 50-100 PRs a week, I need 1 agent that successfully solves the most important problem. I don't understand how you can generate requirements quicky enough to have 10 parallel agents chewing away at meaningful work. I don't understand how you can have any meaningful supervising role over 10 thing…
> don't need 10 parallel agents making 50-100 PRs a week
I don't like to be mean, but I few weeks ago the guy bragged about Claude helping him do +50k loc and -48k loc(netting a 2k loc), I thought he was joking because I know plenty of programmers who do exactly that without AI, they just commit 10 huge json test files or re-format code.
I almost never open a PR without a thorough cleanup whereas some people seem to love opening huge PRs.
Re: The creator of Claude Code's Claude setup
#90This was extremely useful to read for many reasons, but my favorite thing I learned is that you can “teleport” a task FROM the local Claude Code to Claude Code on the web by prepending your request with “&”. That makes it a “background” task, which I initially erroneously thought was a local background task. Turns out it sends the task and conversation history up to the web version. This allows you to do work in othe…
OpenCode is actually client server architecture. Typically one either runs the TUI or the web interface. I wonder if it would cope ok with running multiple interfaces at once? Neovim has a decade old feature request for multiple clients to be able to connect to it. No traction alas. Always a great superpower to have, if you can hack it. https://github.com/neovim/neovim/issues/2161 Chrome DevToops Protocol added multi…
> Neovim has a decade old feature request for multiple clients to be able to connect to it. No traction alas.
Why cram all features into one giant software instead of using multiple smaller pieces of software in conjunction? For the feature you mentioned I just use tmux which is built for this stuff.
Also, OpenCode has been extremely unreliable. I opened a PR about one of the simplest tools ever: `ls`, and they haven't fixed it yet. In a folder, their ls doesn't actually do what you'd expect: if iterates over all files of all folders (200 limit) and shows them to the model...