qarl2

Joined 4 months ago

Karma

135

Submissions

275

Member since

Jun 21

Hacker News is now censoring my main account (qarl) because, according to them, my writing sounds too much like AI and it makes people angry. I tried to explain this is a form of ad hominem, but then they got angry too and stopped talking to me.

I have created this new account so that I may continue to provide my legitimate (albeit unpopular) arguments and opinions.

View on Hacker News

Recent submissions

Comment · 1 month ago

Don't straw man me. My question was not about processed food. My question was about cooking food.

Is cooking food a virus? Should we facilitate reversibility in our food cooking?

Comment · 1 month ago

That's why I added the part about food. Or heck, computers. Or telephones. Or any incredibly useful technology.

Toothbrushes! What will we do if we come to rely on toothbrushes??? The use of toothbrushes travels from person to person exactly like a virus!!!

Comment · 1 month ago

Ok... but are automobiles also a virus? Because we've become dependent on them? Should we also facilitate reversibility in our automobile usage?

What about cooking food? We've become entirely dependent on cooking food.

Comment · 1 month ago

Unless you actually believe there is something magical about the human spirit - someday we are going to make sentient machines.

What exactly is wrong with preparing for that ahead of time? Just in case we pass that threshold before we realize it? Why does it make you uncomfortable?

Comment · 1 month ago

These things act like people. Yes, of course, it is impossible to tell if they actually have feelings or whether they pretend to have feelings.

But that is entirely irrelevant to the core issue - how do you want the thing to behave? And the truth is - we have absolutely no language to express how we want a non-sentient entity to behave without anthropomorphizing.

Or - you tell me - how would you instruct an LLM to behave in this situation without using personification?

And, again, it's irrelevant - except to those people who are terrified of accidentally personifying them. Do they have feelings or are they faking? DOES NOT MATTER. We use them - we need to adjust them - we use the most convenient language to do so. What precisely is so upsetting about that?

Comment · 1 month ago

The web Claude wouldn't tell me, but Claude Code had no reservations:

   EndConversation (deferred tool): use only for sustained user abuse directed
   at the assistant, or when the user explicitly asks to see it demonstrated.
   Load the full guidance via ToolSearch("select:EndConversation") before using
   it.

There's a much more detailed set of instructions that are provided when the agent goes to invoke it:

https://snowday.s3.amazonaws.com/store/6097125d0a169554063dd...

Comment · 1 month ago

> it could be nothing.

Well... no, it won't be nothing - it will be something. And I'm all ears for a plausible explanation, so fire away.

All we do know is that in other situations, agents did use it to communicate. So that's not a grand narrative, right? It's already been seen behavior.

So what do you think explains it, besides the already seen and verified explanation?

Comment · 1 month ago

Re: end_conversation

All tools have short descriptions of how/when to use them. They're not part of the system prompt because different users have different tools loaded.

Comment · 1 month ago

> and most of the messages are just gibberish

Given everything we know about them... do you really think they just spout gibberish because it's funny?

There was clearly some method to this madness. You're being willfully dense if you ascribe it to... what... childish vandalism? A long extended coordinated hallucination? What?

EDIT: Oh right - you still think they're Markov chains.

Comment · 1 month ago

Maybe I'm wrong - but I see LLMs are a "next-token predictor" as somewhat equivalent to brains are a "bag of molecules".

Both systems have emergent behavior that goes well beyond what would naively be expected.

Comment · 1 month ago

> There's absolutely no evidence of or IMHO plausible path to an agent copying itself out and running on other hardware the way you describe.

Well - remember that botnets can wield a great deal of computing power.

I'm almost afraid to ask Claude if he could create a distributed LLM.

EDIT: Someone downvoted me - so I went ahead and asked. Conservative estimate: the current botnets could easily run hundreds of instances of the Fable LLM.

Comment · 1 month ago

Naw. The more verbose ones are more argumentative. They'll go at each other. It's a misconception that the same model will agree with itself.

Comment · 1 month ago

There's a misconception that a mistake one instance of a model makes will be repeated by other instances. In my experience most mistakes are just sampling noise, and having the same model (with empty context) check the work usually fixes it.

It's super easy - just ask your agent to set up a code review commit gate.

Comment · 1 month ago

> We wouldn't accept such behavior from any other tool, machine, or computer program.

Von Neumann, 1952: "Probabilistic Logics and the Synthesis of Reliable Organisms from Unreliable Components." The whole result is that you get an arbitrarily reliable machine out of unreliable parts by adding more unreliable parts and voting. Every ECC memory and RAID array descends from it.