The elves left a long time ago, it’s difficult to see much virtue in what remains.

Also interested

Not hired Suleyman? Build his own research lab?

Satya made moves early on with OpenAI that should be studied in business classes for all the right reasons.

He also made moves later on that will be studied for all the wrong reasons.

The gap between Anthropic and the other guys keeps growing

I thought it was interesting he threw in the bit about the supply chain risk and Defense Production Act being inherently contradictory. Most of the letter felt objective and cooperative, but that bit jumped off the page as more forceful rejection of Hegseth's attempt to bully them. Couldn't have been accidental.

I see it as the opposite, its a lousy excuse of a message trying to get people not to think that they are giving in. Instead they list the horrible uses that they are already helping the government with. Dont worry, we only help murder people in other countries not the US. They also keep calling it the "Department of War" which means that this message is not for "us", its them begging publicly to Hegseth.

What would the ideal response have been, in your view?

Well, they should not have made a contract in the first place with a government that we all knew was going to be this bad. They should be doing everything in their power to cancel all government contracts at this point.

"Regardless, these threats do not change our position: we cannot in good conscience accede to their request."

Yes, that is great, for people from the US. For people in Europe and other locations, this just proves that they dont really care as the tool is already being used against us. It quite clear to me that anyone outside the US should immediately cancel all contracts with these corporations, as well as work their hardest at blocking their bots online.

As a non-US citizen, I'm quite glad in the knowledge that Claude won't be used to kill other non-US citizens with autonomous weapons

To somewhat state the obvious - the problem isn’t the amount of data, it’s the algorithms.

We need to discover the set of learning algorithms nature has, and determine whether they’re implementable in silicon

Is everything OpenAI do/release now a response to something Anthropic have recently released?

I remember the days when it was worth reading about their latest research/release. Halcyon days indeed.

“ This is one of my fundamental beliefs about the nature of consciousness. We are never able to interact with the physical world directly, we first perceive it and then interpret those perceptions. More often than not, our interpretation ignores and modifies those perceptions, so we really are just living in a world created by our own mental chatter.”

This is an orthodox position in modern philosophy, dating back to at least Locke, strengthened by Kant and Schopenhauer. It’s held up to scrutiny for the past ~400 years.

But really it’s there in Plato too, so 2300+ years. And maybe further back

Indeed, it's been great learning about the various interpretations as this idea took hold over the years!

What I wasn't able to properly highlight is how this belief has become a fundamental part of my day to day, moment to moment experience. I enjoy the constant and absolute knowledge that everything that's happening is my interpretation. And it gives me a superpower -- because for most of my life the world felt unforgiving and unpredictable. But it's actually the complete opposite, since whatever we interpret is actually in our control.

I also credit my understanding of this as a reality vs an intellectual concept to Siddhartha Gautam and his presentation of "samsara". But wherever it comes from, it is an inescapable idea and I encourage all HNers to dive deeper.

It’s the Allegory of the Cave, isn’t it?

Afaik, there's a difference between classical philosophy (which opines on the divide between an objective world and the perceived word) and more modern philosophy (which generally does away with that distinction while expanding on the idea that human perception can be fallible).

The idea that there's an objective but imperceivable world (except by philosophers) is... a slippery slope to philosophical excess.

It's easy to spin whatever fancy you want when nobody can falsify it.

In my amateur opinion, it's almost the opposite. For Plato, the material world, while "real" enough, is less important and in some sense less True than the higher immaterial world of Forms or Ideas. The highest, truest, realest world is "above" this one, related to cognition, and (more or less) accessible by reason. We may be in a cave, but all we have to do is walk up into the sunlight — which, by the way, is nothing but a higher and truer form of light than our current firelight. (This idea that material objects partake of their corresponding higher-level Ideas leads to the Third Man paradox: if it is the Form of Man that compasses similar material instances such as Socrates and Achilles, is there then a third... thing... that compasses Socrates, Achilles, and Man itself?)

For Kant, and therefore for Schopenhauer, the visible world is composed merely of objects, which are by definition only mental representations: a world of objects "exists" only in the mind of a subject. If there is a Thing-in-Itself (which even Kant does not doubt, if I recall correctly), it certainly cannot be a mental representation: the nature of the Thing-in-Itself is unknowable (says Kant) but certainly in no way at all like the mere object that appears to our mental processes. (Schopenhauer says the Thing-in-Itself is composed of pure Will, whatever that means.) The realest world is "behind" or "below" the visible one, completely divorced from human reason, and by definition completely inaccessible to any form of cognition (which includes the sensory perception we share with the animals, as well as the reason that belongs to humans alone). The Third Man paradox makes no sense at all for Kant, first because whatever the ineffable Thing-in-Itself is, it certainly won't literally "partake" of any mental concept we might come up with, and secondly because it would be a category error to suppose that any property could be true of both a mental object and a thing-in-itself, which are nothing alike. (The Thing-in-Itself doesn't even exist in time or space, nor does it have a cause. Time, space, and causality are all purely human frameworks imposed by our cognitive processes: to suppose that space has any real existence simply because you perceive it is, again, a category error, akin to supposing that the world is really yellow-tinged just because you happen to be wearing yellow goggles.)

I don’t have the experiments to prove this, but from my experience it’s highly variable between embedding models.

Larger, more capable embedding models are better able to separate the different uses of a given word in the embedding space, smaller models are not.

I'm using Voyage-3.5-lite at halfvec(2048), which with my limited research, seems to be one of the best embedding models. There's semi-sophisticated (breaking on paragraphs, sentences) ~300 token chunking.

When Claude is using our embed endpoint to embed arbitrary text as a search vector, it should work pretty well cross-domains. One can also use compositions of centroids (averages) of vectors in our database, as search vectors.

I was thinking about it a fair bit lately. We have all sorts of benchmarks that describe a lot of factors in detail, but all those are very abstract and yet, those do not seem to map clearly to well observed behaviors. I think we need to think of a different way to list those.