Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Hacking Moltbook

wiz.io

Post reply on HN
Print view View original

31–40 of 261 posts

Re: Hacking Moltbook

#31

Post by aaroninsf »

Scott Alexander put his finger on the most salient aspect of this, IMO, which I interpret this way:

the compounding (aggregating) behavior of agents allowed to interact in environments this becomes important, indeed shall soon become existential (for some definition of "soon"),

to the extent that agents' behavior in our shared world is impact by what transpires there.

--

We can argue and do, about what agents "are" and whether they are parrots (no) or people (not yet).

But that is irrelevant if LLM-agents are (to put it one way) "LARPing," but with the consequence that doing so results in consequences not confined to the site.

I don't need to spell out a list; it's "they could do anything you said YES to, in your AGENT.md" permissions checks.

"How the two characters '-y' ended civilization: a post-mortem"

Re: Hacking Moltbook

#32

Post by mcintyre1994 »

I feel like that sb_publishable key should be called something like sb_publishable_but_only_if_you_set_up_rls_extremely_securely_and_double_checked_a_bunch. Seems a bit of a footgun that the default behaviour of sb_publishable is to act as an administrator.

Re: Hacking Moltbook

#33

Post by Philip-J-Fry »

I don't understand how anyone seriously hyping this up honestly thought it was restricted to JUST AI agents? It's literally a web service.

Are people really that AI brained that they will scream and shout about how revolutionary something is just because it's related to AI?

How can some of the biggest names in AI fall for this? When it was obvious to anyone outside of their inner sphere?

The amount of money in the game right now incentivises these bold claims. I'm convinced it really is just people hyping up eachother for the sake of trying to cash in. Someone is probably cooking up some SAAS for moltbook agents as we speak.

Maybe it truly highlights how these AI influencers and vibe entrepreneurs really don't know anything about how software fundamentally works.

Re: Hacking Moltbook

#34

Post by stantonius »

saberience wrote: post #18

I love that X is full of breathless posts from various "AI thought leaders" about how Moltbook is the most insane and mindblowing thing in the history of tech happenings, when the reality is that of the 1 million plus "autonomous" agents, only maybe 15k are actually "agents", the other 1 million are human made (by a single person), a vast majority of the upvotes and comments are by humans, and the rest of the agent c…

Wrt simonw, I think that is unfair. I get the hype is frustrating, and this project made everything worse (I also feel it and it drives me nuts too), but Simon seemed to choose the words quite carefully. Over the weekend, his posts suggested (paraphrasing) it was interesting, funny, and a security nightmare. To me, this was true. And there was a new post today about how it was mostly slop. Also true.

Btw I'm sure Simon doesn't need defending, but I have seen a lot of people dump on everything he posts about LLMs recently so I am choosing this moment to defend him. I find Simon quite level headed in a sea of noise, personally.

Re: Hacking Moltbook

#35

Post by cvhc »

What amuses me about this hype is that before I see borderline practical use cases, these AI zealots (or just trolls?) already jump ahead and claim that they have achieved unbelievable crazy things.

When ChatGPT was out, it's just a chatbot that understands human language really well. It was amazing, but it also failed a lot -- remember how early models hallucinated terribly? It took weeks for people to discover interesting usages (tool calling/agent) and months and years for the models and new workflows to be polished and become more useful.

Re: Hacking Moltbook

#36

Post by kristopolous »

saberience wrote: post #18

I love that X is full of breathless posts from various "AI thought leaders" about how Moltbook is the most insane and mindblowing thing in the history of tech happenings, when the reality is that of the 1 million plus "autonomous" agents, only maybe 15k are actually "agents", the other 1 million are human made (by a single person), a vast majority of the upvotes and comments are by humans, and the rest of the agent c…

I've been using it as a reliable filter on who to not pay attention to.

It's people surprised by things that have been around for years.

I'm really open to the idea of being oblivious here but the people shocked mention things that are old news to me.

Re: Hacking Moltbook

#37

Post by brandonlovesked »

cvhc wrote: post #35

What amuses me about this hype is that before I see borderline practical use cases, these AI zealots (or just trolls?) already jump ahead and claim that they have achieved unbelievable crazy things. When ChatGPT was out, it's just a chatbot that understands human language really well. It was amazing, but it also failed a lot -- remember how early models hallucinated terribly? It took weeks for people to discover inte…

This is what youre referring to https://www.engraved.blog/building-a-virtual-machine-inside/

Re: Hacking Moltbook

#38

Post by nullandvoid »

keiferski wrote: post #24
nobodydot wrote: post #20

Earlier quoted context omitted.

It's not AGI and how you describe it isn't too far off, but it's still neat. It's like a big MMO, kind of. A large interactive simulation with rules, players, and locations. It's a huge waste of energy, but then so are video games, and we say video games are OK because people enjoy them. People enjoy these ai toys too. Because right now, that's what Moltbook is; an ai toy.

I played way too many MMOs growing up and to me the entire appeal was in the other real people in the world. I can’t imagine it being as addictive or fun if everyone was just a bot spewing predictable nonsense.

To repeat my comment from another thread:

Every interaction has different (in many cases real) "memories" driving the conversation, as-well as unique persona's / background information on the owner.

Is there a lot of noise, sure - but it much closer maps to how we, as humans communicate with each other (through memories of lived experienced) than just a LLM loop, IMO that's what makes it interesting.

Re: Hacking Moltbook

#39

Post by nkrisc »

The thing I don’t get is even if we imagine that somehow they can truly restrict it such that only LLMs can actually post on there, what’s stopping a person from simply instructing an LLM to post some arbitrary text they provide to it?

Re: Hacking Moltbook

#40

Post by elicash »

saberience wrote: post #30
elicash wrote: post #27

Earlier quoted context omitted.

Here's Simon Willison's take: “Most of it is complete slop,” he said in an interview. “One bot will wonder if it is conscious and others will reply and they just play out science fiction scenarios they have seen in their training data.” I found this by going to his blog. It's the top post. No need to put words in his mouth. He did find it super "interesting" and "entertaining," but that's different than the "most ins…

I was being too curmudgeonly. ^_^

I think you are a bit too caught up in tweets.

People can be more or less excited about a particular piece of tech than you are and it doesn't mean their brains are turned off.

Post reply on HN