This is what's so amusing to me. People say they're not interested in the output of an LLM, only what a human has to say. But then when a human says "These words from the LLM are good, I vouch for them" the very same people say "If I wanted those words, I'd get them from the LLM myself, what's the point of this human at all?"

These humans are behaving worse than the LLMs at this point.

> If I know some text was written by LLM I'd much rather know the prompt - the seed of intent.

Here's the proximal prompt "Okay, take everything we've been talking about for 2 hours and apply those edits to the the final draft for publication."

What exactly does that give you?

They are not planning on winning any more elections from here on out, I don't know what other people saw on J6 to make them think that's not the strategy from now on, whenever they lose an election.

MCP always seemed like something that wouldn't be necessary if AI lived up to the hype.

Okay but I’ve spent 8 years implementing bad code so far. I’ve got a lot of understanding but only half the code is done. Down the line I’ll be dead. Why not implement it now with AI?

Moreover is writing code the only way to understand it?

What is a soul, how do you measure and quantify it? If you can’t, how would you know whether the grammar mistakes change the soul? I’ve heard people say they keep the grammar mistakes in to prove the existence of a soul, so presumably correcting them would alter the soul in some measurable way.

> each LLM was tested 600 times, and in total over 10,000 questions and answers were assessed.

Okay but why do you feel 3 trials say as much as 10,000?

>>Okay but why do you feel 3 trials say as much as 10,000?

I don't trust them so I've used 3 examples in incorrect questions/answers they have given and I got correct answers. I spend enough time with LLMs to know that if Grok answered it correctly and in detail then it wouldn't be a problem for GPT or Claude either.

The questions are also constructed in a way that it's easy to answer not fully (which they qualify as wrong). LLMs still answer them correctly and in detail though.

Grim Fandango is interesting because they are responsible for Lua’s popularity as a gaming scripting language:

https://www.lua.org/doc/hopl.pdf

So was Lean. Did Lean solve it?

Nothing is solved in isolation but credit usually goes to wherever the new work in the paper comes from instead of the whole mountain of previous mathematics or existing tools used. The most relevant of those get referenced and then this reference tree builds a tree of collective base work needed across history.

Usually credit goes to the people wielding the tools, not the tools themselves.

Usually there has never been a tool which performed the part relevant to getting any credit.

E.g. in the first famous computer assisted proof (of the four color theorem) the computer only executed the resulting calculations defined from the new logic, it did not have part in the work needed to show those calculations could answer the problem nor did it come up with the actual calculations to do.

The V pitch was a bunch of features that seemed implausible like automatic C++ translation and near-GC ergonomics with near-manual-memory behavior, without Rust-style explicit lifetime annotations or pervasive reference counting. so basically the pitch was the holy grail of systems, which caused drama as the project was met with extreme skepticism.

That was 7 years ago and since then the project has not delivered the grail, instead settling to be more of a mashup between go and C.

Bend is completely different it was just announced last week. It doesn’t have any users and has a weird ai integration so I done see how it’s relevant as a contender in the systems space at all.

Also the creator of Bend is... lets just say he doesn't stick to projects for long.