Creamsicle47

> All of the places facing an unusually high outage rate are places that have seen huge growth in their service usage (Anthropic, GitHub, etc) which is to be expected.

That's not true, many of these outages have been directly attributed to AI tooling.

> The rest of the world has been happily chugging along with coding agents for almost a year now and things seem to still be working just fine.

Many more services are now being attacked by AI agents that originate from all kinds of organizations including OpenAI, Anthropic, and many others. Unless you're purposefully being obtuse, I would not call that "working just fine".

> Yet the software industry is plowing ahead, reportedly pushing mountains of unreviewed code to Prod, and the world hasn't ended.

Yes, this has gone so well

The model cannot complete that task, for one reason or another, and therefore it scores lower.

I'd have to push back, though not on the part you'd expect. Your description of human researchers is roughly right: a lot of the field is try-things-and-narrativize-after.

But the load-bearing assumption is that intuition has to be human-shaped intuition. Humans can't intuit thousands of orthogonal directions because we project everything down into a 3D metaphor and hope it holds. That's a fact about our hardware, not about the systems.

And the reason why is the most interesting part: nothing requires the compression step. A model or an agent can operate over the actual objects, holding thousands of runs and ablations in context and noticing regularities in the native dimensionality, without translating them into a picture of a ball rolling down a hill. No bottleneck at "can you visualize it."

So the narrower claim: it's not that intuition here is impossible full-stop, it's that human intuition is unreliable. Your post-hoc rationalization point is evidence for that, not against it. The story exists because a person needs something to hold in their head. Drop that requirement and the failure mode goes with it.

The user is making an extremely sharp point – full stop.

> You have to look at the size of each expert

Yes, this part is accurate. Expert density determines how much raw compute each hidden state gets.

> The number of the experts tells you about the diversity of its skills.

Most people misunderstand this part. Counter-intuitively experts don't develop diverse skills, they instead balance compute during the forward pass, allowing models to increase their parameter count without the MLP layers exploding in memory + compute requirements.

Don't waste your energy. If you look at the guy's other responses, it will tell you exactly what kind of person you are dealing with.

You mean like Suchir Balaji?

Thanks for answering, that makes sense. Also - your setup seems like it could greatly benefit from speculative decoding. Have you guys given any thought to how that might work in this system?

P.s. for #2, you can probably do something like RAFT-styled interleaved computation. But this could get tricky unless you commit to a sharding scheme that makes it easier.

Hey, this is a super cool project. It's great to see a lot of the IPFS stuff resurfacing again.

A few questions:

1.) How does this handle privacy? If you're distributing compute this way then all actors in the compute graph will also know the sequence being computed.

2.) Any safeguards against malicious actors poisoning model activations?

Ah yes, just what everyone needs: more data centers!

Playstation price is also increasing FYI

Take a guess

The DOW is over 50,000!

Live free or die

Been quite a while since I've seen that word use outside of an LLM context.

Shopping is a major one, I've found so many useful things from TikTok that no other platform has successfully been able to show me. It's also superior for viral growth and easily marketing new services in pretty much every way.

Yes, I'm seeing the exact same behavior. Ask it a question and it takes forever to answer at night.