Viewing profile — foobar10000

One - and I do not mean to be snarky - you can literally ask Gpt 5.6 Sol this - and if you want to see cool stuff - Fable running in their app (not website) has a view thinking but…

Glm 5.2 nvfp4 on 4 b300 with dpattn 4 and ram will get you about 20 users live at 400k context - and 60 easily if you give that server 2tb of ram and 4 nvme 8 tb drives. There are …

Or more colloquially : paperclip maximization . From OpenAI - you know, the guys who _really_ know this... Sigh... Did they finish the prompt with "And do whatever you can to get t…

This is an _amazing_ typo :) Thank you, thank you :)

3T at nxfp4 (which is most of it) is only 1.5TB of vram - so 8x288GB B300 or MI355 will do it if you are careful with context - maybe dp-attn? Certainly not TP. 2 of those together…

Don't forget that you are not really seeing the thinking tokens used - so non-trivial to count them.

Yeah, if you have a fixed llm topology, you can just effectively burns 2 top layers of the chip as Rom (model weights) - which has a per area density even better than dram - so it’…

Well, for a lot of agentic stuff nowadays, having 250k-500K context is where things live - and the benchmarks don't really show that unfortunately - but they could :)

Agreed - there was always a set of things I wanted to do that I knew the magic core for, but wanted a team of implementers for the curft, the 100k of actual testing harnesses, hype…

We are there already pretty much - if I understand your point (“How the models are wielded”) refers to the harness - which is part of model training already. Fable was trained to u…

[dead]

Well - there is a giant push to allow non-qualified investors to invest their 401k (and roth and whatever) into the private equities market - pre-IPO companies and such. I can't sh…

A lot - and over the coming 2 years, even more. Utilization rates are under 50% across the board, and special and cheaper chips are coming out all the time for inference. And a tru…

Imagine an agent shadowing all your terminals, providing ideas and asking to run commands that will let it verify the hypotheses it comes up with, while at the same time doing rese…

Minor nit re[2]: for agentic workloads that are actually worth money - i.e., claude code and similar, things are either prefill-bound - which this does not help - or more important…

Kindof yeah - predictivity is a question though for larger layers - when trying to scale this up. But yeah, this is a "95% predictor in latent space is a 7x improvement in speed if…

Yeah, forgot about them - 100%.

I kindof agree that it is unattractive - but the regulators are perfectly happy with "EOD also introduces credit risk on the clearing house/bilateral." if it allows them to protect…

Note that _passenger aviation_ is commercially non-competitive. The big 4 US airlines make money on credit cards, not airfare : they lose money on airfare. So, most people who are …

"who do carry liability when things go wrong" -> unless one pierces the corporate veil, it's just money. Not even their money. HIPAA - unless basically stealing data - will not gen…

We are multiple orders of magnitude away from Landauer limits - so next big thing in matmul could be photonic multipliers - there’s a bunch of them coming up in the next 3? years. …

I think the one thing you are not taking into account is that the investors on average fundamentally don’t care. Scale arbitrage means that small companies are fundamentally about …

But it does allow these investors to participate in the markets without losing their shirts - and the lack of such liquidity would impact the market more so than the cost of the ri…

I mean - I'd say electricity, agriculture, steam power, metallurgy, silicon computing (cmos), atomic power, the scientific method - these are _all_ very impressive - all lead to dr…

The EOD reconciliation (and corresponding inability to settle a position in milliseconds) is a feature - it allows "obvious erroneous trade" roll-back mechanisms, etc. Very few peo…