Viewing profile — generallyjosh

Did it make any mistakes on your taxes? Personally, I know coding pretty well. So when I'm using it for coding, I can spot most of its mistakes / misunderstandings I would not trus…

Well, you said: The potential of the current crop of LLM/AIs will stop at being a very powerful tool to search large volumes of text using free-form questions. I do think that pret…

Hey you can try it if you like. That's one of the beauties of the current moment, nobody REALLY knows what works best, just a whole lot of people trying stuff And no, I wouldn't ev…

Larger models need more hardware resources to run And, depending on effort settings, they do more 'thinking', i.e., use more rounds of inference to generate longer internal chains …

The problem isn't giving MORE context to an agent, it's giving the right context These things are built for pattern matching, and if you keep their context focused on one pattern, …

I'd assume it probably depends how large and varied your logs are? But, my guess, I could see an algorithm like that being very fast. It's basically just doing a form of compressio…

I think what most people are worried about is that, as you say, AGI won't necessarily have our biases/biological drives That might also mean it has no drive for self-determination.…

You say this as though it's a pithy point. Might as well say humans are just a better search tool - it's true in the exact same sense you're using. All humans do is absorb informat…

The whole point of an economy is to generate value. Very, very different than caring for people Feudalism was the dominant economic system for millennia. The point is to extract va…

There are lots of intelligent people looking at AI and imagining its potential Are you just saying that you're more intelligent than them? You can see clearly, where all the steam …

Openclaw isn't new (and the actual project never made itself out to be new) It's a nice packaging, of a whole bunch of preexisting things. Agentic AI inside a nice sandbox containe…

I do strongly agree on the framing, but I'd argue with the conclusion Yeah, it really doesn't matter if AGI has happened, is going to happen, will never happen, whatever. No matter…

I'm finding the latest models are pretty good at debugging, if you give them the tools to debug properly If they can run a tool from the terminal, see all the output in text format…

One of the first skills I made for Claude was a research skill. I give it a question (narrow or really broad), and the model does a bunch of web searches using subagents, to try an…

I do think there's value in trying out fully vibe coding some toy projects today (probably nothing real or security sensitive haha). The AI will get better at compensating, but I t…

That mirrors my experience so far. The AI is fantastic for prototyping, in languages/frameworks you might be totally unfamiliar with. You can make all sorts of cool little toy proj…

All we can do is try our best to look at the world with clear eyes, and think about where the industry's going over the next couple years Not how we want things to be, but how they…

IMO, documentation becomes much more important if we're planning to hand off coding to the LLMs You can ask it about the code, sure, and it'll try to tell you how it works. But, wh…

I do think there is some actual value in telling an LLM "you are an expert code reviewer". You really do tend to get better results in the output When you think about what an LLM i…