Because OpenClaw (well, all AI) is well known for following instructions correctly.

https://au.pcmag.com/ai/116091/meta-security-researchers-ai-...

> "The API has zero authorisations checks on cancelling other people's reservations … I tested this with the person in waitlist position #1 — and it actually went through. So you've moved from #4 to #3 already," it messaged back.

The AI systemm didn't hack anything, it lightly touched with a feather duster and the server crumbled.

The AI system probably found swagger documentation of each endpoint, figured that the reservation cancellation API was worth a shot, and then found there was no authentication.

What is the "hack" here?

I find it ironic that the people who originate the idea of AI-code-spam are being negatively impacted by this.

But all they will do is build an AI agent to review the code written by an AI agent, that probably never needed to be written to begin with.

Comments URL: https://news.ycombinator.com/item?id=48608472

Points: 1

# Comments: 0

A human also knows they might get punished if it messes up bad enough, which might cause it to think twice before doing something bad. For an AI there is a reward, but there is no risk.

So while both might lie, only the human will be worried that it will be found out. That makes a difference.

You are publicly proposing “throwing all Republicans through a window to their death”.

This isn’t normal, and it isn’t right. If we allow anyone to call for political violence, then we become numb to it. Worse still, your call to violence against Republicans gives them a call to defence, and then a call to preemptive action.

“It was ok for us to shutdown HackerNews because they called for our deaths.”

We shouldn’t tolerate calls to political violence from anyone. Be better.

https://www.washingtonpost.com/opinions/2021/10/29/schools-a...

So does the National Council of Teachers of English. https://ncte.org/teaching-maia-kobabe/

Just because can't believe that people would promote a comic with explicit texting and sexual imagery to children doesn't mean it doesn't happen.

Secondly, this is pure AI slop. There are 2 commits - "Initial commit" and "Trim feature table" where you changed the README.

Why would anyone use this? Has anyone read any of the code? Do you even understand how (or if) it even works?

Surely, it would be a flex to show that your AI agents are so good they make electron redundant.

But they don’t. So it’s reasonable to ask why that is.

This is a goregous way of presenting a book, and what looks like subscriber only chapter previews.

Comments URL: https://news.ycombinator.com/item?id=46666582

Points: 3

# Comments: 1

LLMs offer a level of flexibility and non-determinism that allow them to adapt to different situations.

GUIs offer precision and predictability - they are the same every time. Which means people can learn them and navigate them quickly. If you've ever seen a bank teller or rental car agent navigate a GUI or TUI they tab through and type so quickly because they have expert familliarity.

But this - with a non-determinstic user interface generated by AI, every time a user engages with a UI its different. So they a more rigid UI but also a non-deterministic set of options every time. Which means instead of memorising what is in every drop down and tabbing through quickly, they need to re-learn the interface every time.

Yes.

This is exactly how LLMs work. For a given input, an LLM will output a non-deterministic response that approximates its training data.

LLMs aren’t intelligent. And it isn’t that they don’t learn, they literally cannot learn from their experience in real time.

Your post reads like AI precisely because while the grammar is fine, it lacks context - like someone prompted “reply that AI is better than average”.