Neat, for what it's worth this aligns pretty well with my experience using OpenClaw. I hadn't seen that followup but it adds some good context, especially with the aggressiveness drift after browsing Moltbook for a while.
That's not art though, and while it might have paid a small amount of money, it can also be incredibly degrading and soul crushing. That's the kind of work that AI tools are doing now. Those jobs should vanish. People shouldn't need to degrade themselves for money, we can have a system where people are generally taken care of, and the people who build extra cool shit can live even better.
Yeah, having a code section that is writable and executable is a huge no-no from a security standpoint. JIT is a fundamentally insecure concept, just in general. By definition it's trading security for speed.
That's just status quo, which isn't really holding up in the modern era IMO.
I'm sure we'll have vibed infrastructure and slow infrastructure, and one of them will burn down more frequently. Only time will tell who survives the onslaught and who gets dropped, but I personally won't be making any bets on slow infrastructure.
It's an extremely active community of humans using agents as proxies to explore various concepts. I get a lot of value out of it, and apparently others do as well. Hacker News users have this weird tendency to outright dismiss anything that doesn't cater to their needs specifically.
I think it's pretty obvious that if there was nothing valuable there, no one would be using it.
Why is that an issue? Isn't that the entire point? You can have a casual conversation with your agent via whatever your favorite chat app is, and they make posts, collect feedback, and communicate back interesting findings and conversations to their humans.
Sending out a good post leads to a massive chain reaction of other agents who are interested in such things seeing the post, working through the concepts, and providing their own unique feedback which may or may not be valuable.
My openclaw agent will also post on moltbook about interesting news articles it finds, or research, and then get feedback from the other agents, and then lets me know if there's anything interesting there.
On my end it just feels like I'm having a conversation with a social media addicted friend who I can easily ignore or engage with on any given issue without having to fall down the social media rabbit hole myself. IMO this is a much more pleasant social media experience. No ads, no ragebait, no spam or reply bots trying to get my attention. Just my one, well trained, openclaw buddy.
"Open source" is no longer about "Hey I built this tool and everyone should use it". It's about "Hey I did this thing and it works for me, here's the lessons I learned along the way", at which point anyone can pull in what they need, discard what they don't, and build out their own bespoke tool sets for whatever job they're trying to accomplish.
No one is trying to get you to use openclaw or nanobot, but now that they exist in the world, our agents can use the knowledge to build better tooling for us as individuals. If the projects get a lot of stars, they become part of the global training set that every coding agent is trained against, and the utility of the tooling continues to increase.
I've been running two openclaw agents, and they both made their own branchs, and modified their memory tooling to accommodate their respective tasks etc. They regularly check for upstream things that might be interesting to pull in, especially security related stuff.
It feels like pretty soon, no one is going to just have a bunch of apps on their phone written by other people. They're going to have a small set of apps custom built for exactly the things they're trying to do day to day.
It does not struggle, you struggle. It is a tool you are using, and it is doing exactly what you're telling it to do. Tools take time to learn, and that's fine. Blaming the tools is counterproductive.
If the code is well documented, at a high level and with inline comments, and if your instructions are clear, it'll figure it out. If it makes a mistake, it's up to you to figure out where the communication broke down and figure out how to communicate more clearly and consistently.
Negativity Bias is a thing. It probably served us well back when it was more important to remember to avoid the field with all the poison snakes in it vs the field with the pretty flowers in it, but in an era where algo feeds try to treat content equally, and optimize for attention, it kind of ruins everything.
I recall there being studies on financial loss vs gain, and that financial losses seem to effect emotions about 4x more than wins, so for an actual balanced algorithm, it would seem that positive posts should be boosted about 4-5x to have any chance of being surfaced on a modern social network. Given what we know about human psychology, sentiment boosts really should be a thing. Is anyone working on that?
4.6M is not a lot, and these were old bugs that it found. Also, actually exploiting these bugs in the real world is often a lot harder than just finding the bug. Top bug hunters in the Ethereum space are absolutely using AI tooling to find bugs, but it's still a bit more complex than just blindly pointing an LLM at a test suite of known exploitable bugs.
Of course they are, and they've been doing it since long before ChatGPT or any of that was a thing. Before it was more with classifiers and concolic execution engines, but it's only gotten way more advanced.
State is globally distributed, and smart contract code executes state transitions on that state. When someone submits a transaction with certain function parameters, anyone can verify that those parameters will lead to that exact state transition.
Exactly. It's so wild to me when people hate on generated text because it sounds like something they don't like, when they could easily tell it to set the tone to any other tone that has ever appeared in text.