The utility of a program like Excel, Obsidian, Notion, Unity, Jupyter, or Emacs far beyond the knowledge of knowing how to use the product.
All of these products are hammers with nails as far as your creativity will take you.
Its wild to have be on a website called Hacker News, talking about a product that can make a computer do seemingly anything, and insisting its a tool in search of a problem.
Extensible coding agent written in typescript. It’s exactly what you (I’m projecting) want out of Claude Code if you’re okay investing time into building your harness or prompting an agent to build it.
Ya, openclaw is overkill for rewriting a codebase, especially when you're paying API costs.
I developed my own task tracker (github.com/kfcafe/beans), i'm not sure how portable it is; it's been a while since i've used it in claude code. I've been using pi-coding-agent the past few months, highly recommend, it's what's openclaw is built on top of. Anthropic hasn't shut down Oauth, they just say that it's banned outside of Claude Code. I'd recommend installing pi, tell it what you were doing with openclaw and have it port all of the information over to the installation of pi.
you could also check out ralph wiggum loops, could be a good way to rewrite the codebase. just write a prompt describing what you want done, and write a bash loop calling claude's cli pointed at the prompt file. the agent should run on a loop until until you decide to stop it. also not the most efficient usage of tokens, but at least you will be using Claude Pro and not spending money on API calls.
I'm kinda doing this in a back-and-forth way over each section with openclaw, and one nice thing is that I've got it including the chat log for changes with each commit. I'm happy about how it's handled my personality as needing to understand all the changes it's making before committing. So I kind of want something interactive like that -- this isn't a codebase I can trust an LLM to just fire and forget (as evidenced by some massive misunderstandings about rewiring message strings and parameter names like "_meta" and ".meta" and "_META" that meant completely different things which the LLM accidentally crossed and merged at some point, before I caught it and forced it to untangle the whole mess -- which it only did well because there were good logs).
I sort of do need something with persistent memory and personality... or a way to persist it without spending a lot of time trying to bring it back up to speed... it's not exactly specific tasks being tracked, I need it to have a fairly good grasp on the entire ecosystem.
how big is the codebase? how often is the agent writing to memory? you might be able to get away with just appending it to the project's CLAUDE.md? you might also want to check out https://github.com/probelabs/probe
Hm. That looks a lot more granular, which is interesting... I'm not sure it would help me on this.
The codebase is small enough that I can basically go and find all the changes the LLM executed with each request, and read them with a very skeptical eye to verify that they look sane, and ask it why it did something or whether it made a mistake if anything smells wrong. That said, the code I'm rewriting is a genetic algorithm / evaluation engine I wrote years ago, which itself writes code that it then evaluates; so the challenge is having the LLM make changes to the control structure, with the aim of having an agent be able to run the system at high speed and read the result stream through a headless API, without breaking either the writing or evaluation of the code that the codebase itself is writing and running. Openclaw has a surprisingly good handle on this now, after a very very very long running session, but most of the problems I'm hitting still have to do with it not understanding that modifying certain parameters or names could cause downstream effects in the output (eval code) or input (load files) of the system as it's evolving.
Empathy for other living things isn't a fair framing for the problem? what?? Eating less meat being difficult, expensive, or complicated do to health issues are excuses. Most people don't even try to consume less animal products.
The riches of capitalism is built off of the suffering of humans, that doesn't mean it isn't important to try to minimize the suffering of other animals that literally have no ability to escape their circumstances.
I started writing (aka prompted Claude to write) beans after using Steve Yegge's beans, but wanted something with better human auditability so beans uses a markdown with YAML frontmatter and a simple ID system with support for hierarchy and dependencies. It uses verify gates as default for red/green TDD. It has subagent orchestration built-it and should support different agents (I've only tested it with Pi, but should support Claude, opencode, etc).
this might be controversial and a sign of growing up in America, but i think its a lot like people preferring Celsius over Fahrenheit. I don't care if water boils and freezes at exactly 100 and 0 degrees, it's easy to know its state by looking at it. But its very easy to understand what temp differences will feel like between 90, 70, 50 degrees F etc compared to 31, 22, and 4 degrees C.
In the same way, I have absolutely zero idea of what 90, 70 or 50 degrees Fahrenheit feels like - literally no intuition, those numbers seem foreign and disconnected from my experience, having always known and used Celsius. Celsius temperatures just make sense to me. It's literally just about growing up with it.
It's what someone might come up with without a scientific definition. Think of 0 - 100 F being (very very roughly) the survivable range for humans without special precautions beyond normal winter/summer clothes. -18 - 38 C is way more arbitrary from that perspective.
They said there's no intuition there, I gave them one. I didn't say this was how it was defined, just how it could make more sense in daily life than the Celsius range without relying on familiarity.
- 0C - 30C are nice round numbers that are much better numbers for human comfort than 0F and 100F are.
- above 0C in the winter means "it's going to be messy outside", and is the most important number.
- 100C is an important number for cooking
- a degree C is a reasonable interval. People using degrees F tend to round to multiples of 5, which is too large especially around room temperature, but a single degree F change is imperceptible.
So because we're used to it? I know perfectly how those C numbers will feel. Haven't got a clue about the F numbers.
Anyway, I doubt that that analogy goes for noon. I eat lunch by the clock, not when the sun's highest. I expect most people do. Especially the ones that are cooped up in an office during the daytime.
As someone who grew up in America but lived abroad a few years, you just start using different markers but it's the same idea. Something like 0, 10, 15, 20, 30, 40 gives you the full range from freezing to pleasant to very hot.
The Biden administration met seven of the requirements on the list. Do you seriously believe this essay offers any value at all? It’s pop culture trash.
The utility of a program like Excel, Obsidian, Notion, Unity, Jupyter, or Emacs far beyond the knowledge of knowing how to use the product.
All of these products are hammers with nails as far as your creativity will take you.
Its wild to have be on a website called Hacker News, talking about a product that can make a computer do seemingly anything, and insisting its a tool in search of a problem.
reply