Allow your OpenClaw to feed your pet reptile?

I am already there with a project/startup with a friend. He writes up an issue in GitHub and there is a job that automatically triggers Claude to take a crack at it and throw up a PR. He can see the change in an ephemeral environment. He hasn't merged one yet, but it will get there one day for smaller items.

I am already at the point where because it is just the two of us, the limiting factor is his own needs, not my ability to ship features.

Must be nice working on simple stuff.

Why doesn’t he merge them?

He is not technical but a product guy, so he still wants me to check it over.

> But the concept is rooted in the idea of encouraging carmaker employees to buy what they build.

Absent of course is any introspection from management on why such coercion is required.

What the masses have found entertaining has always been referred to as slop, so I am not sure it matters.

Novels, cinema, television, comic books, etc.

They were all considered careless skill-free slop at some point.

I am deeply baffled by AI denial at this point.

Complete denial that AI/LLMs can produce novel, good things is an indefensible stance at this point. But the large volume of AI slop is still an unsolved problem, and the claim that "AI will still mostly deliver slop" seems to be almost certainly correct in the near-term.

We've had a few decades to address email spam, and still haven't manage to disincentivize it enough to stop being the main challenge for email as a communication medium. I don't think there's much hope that we'll be able to disincentive the widespread, large-scale creation of AI slop even after more expensive models with higher-quality output are available.

you are posting in a thread about it finding a novel solution to an unsolved mathematics problem

> And it is on a portion of the Start menu that can be fully disabled.

I mean, with tons of effort and config Windows can be turned into a usable OS. Needing to do all that is a huge part of the problem.

Exactly, use linux instead. Windows sucks donkey dicks, its hilarious how hard you defend it.

Yep. In many cases I am just reviewing test cases it generated now.

> if it breaks, let agents fix it, no manual debugging needed!" ?

Pretty trivial to have every Sentry issue have an immediate first pass by AI now to attempt to solve the bug.

> agent try everything that the LLM chatbot had recommended ($$$)

A lot depends on whether it is expensive to you. I use Claude Code for the smallest of whims and rarely run out of tokens on my Max plan.

Our experiments aren’t free. We use cloud infrastructure. An experiment costs on the order of tens of dollars, so massively parallelizing “spaghetti at wall” simulators is costly before we even talk about LLMs.

If it is an experiment. Can’t you just make a POC for the experiment that doesn’t need to use half of AWS to just run? And if the experiment is actually positive you can then bring it to the real application and test it there (and spending the 10-100 usd it costs to test it live)?

I wouldn’t want the LLM-based agent to hyperspecialize its solution to a subset of the data. That’s a basic tenet of machine learning.

Steelmanning your question though, I guess you could come up with some sort of tiered experimentation scheme where you slowly expose it to more data and more compute based on prior success or failures.

Craftsmen have consistently vastly overestimated where the floor is for the quality customers will accept, from clothing to shoes to system security to how much RAM a piece of software uses.

Customers consistently prefer cheap.

There will always be a few niche cases where someone values something more, but not at the mass market.

Yes, people think this behaviour came out of nowhere. It’s because if you are younger, phone calls are not the default (only two friends ever call me) and overwhelmingly are scammers or salespeople.