461–470 of 603 posts
Earlier quoted context omitted.
Well, imagine this was controlling a weapon. “Should I eliminate the target?” “no” “Got it! Taking aim and firing now.”
It is completely irresponsible to give an LLM direct access to a system. That was true before and remains true now. And unfortunately, that didn't stop people before and it still won't.
What else is an LLM supposed to do with this prompt? If you don’t want something done, why are you calling it? It’d be like calling an intern and saying you don’t want anything. Then why’d you call? The harness should allow you to deny changes, but the LLM has clearly been tuned for taking action for a request.
> What else is an LLM supposed to do with this prompt? Maybe I saw the build plan and realized I missed something and changed my mind. Or literally a million other trivial scenarios. What an odd question.
I don't see anything odd about this question.
What kind of response did the user expect to get from LLM after spending this request and what was the point of sending it in the first place?
Earlier quoted context omitted.
> And on top of it, if you develop for native macOS, There’s no official tooling for visual verification. It’s like 95% of development is web and LLM providers care only about that. Thinking out loud here, but you could make an application that's always running, always has screen sharing permissions, then exposes a lightweight HTTP endpoint on 127.0.0.1 that when read from, gives the latest frame to your agent as a P…
Yeah, this is pretty much how Tidewave works, but passes the HTML/JavaScript reference instead of a picture: https://tidewave.ai/
Earlier quoted context omitted.
I feel like people are sleeping on Cursor, no idea why more devs don't talk about it. It has a great "Ask" mode, the debugging mode has recently gotten more powerful, and it's plan mode has started to look more like Claude Code's plans, when I test them head to head.
In the coworking I am in people are hitting limits on 60$ plan all the time. They are thinking about which models to use to be efficient, context to include etc… I’m on claude code $100 plan and never worry about any of that stuff and I think I am using it much more than they use cursor. Also, I prefer CC since I am terminal native.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…
> I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look If 3 years into LLMs even HNers still don't understand that the response they give to this kind of question is completely meaningless, the average person really doesn't stand a chance.
This is way too strong isn't it? If the user naively assumes Claude is introspecting and will surely be right, then yeah, they're making a mistake. But Claude could get this right, for the same reasons it gets lots of (non-introspective) things right.
It’s fascinating, even terrifying how the AI perfectly replicated the exact cognitive distortion we’ve spent decades trying to legislate out of human-to-human relationships.
We've shifted our legal frameworks from "no means no" to "affirmative consent" (yes means yes) precisely because of this kind of predatory rationalization: "They said 'no', but given the context and their body language, they actually meant 'just do it'"!!!
Today we are watching AI hallucinate the exact same logic to violate "repository autonomy"