Re: Acceleration

Tu as très bien compris ce que je voulais dire

C’est toi qui n’a pas compris ce que je voulais dire, je pense.

1. Ce qu’il se passe si le vent tourne... tu n’en sais rien. Et moi non plus. Les comptes de OpenAI ne sont pas publics. Si le vent tourne, ça veut dire qu’ils coupent la R&D et l’entraînement de nouveaux modèles, baissant drastiquement leurs coûts. Sont-ils positifs après ces coupes ? Toujours négatifs ? Qui sait ?

2. Mais le fond de la question est que le vent souffle dans ce sens pour une bonne raison, et qu’il va falloir que la raison disparaisse pour que le vent arrête de souffler. François Chollet l’explique mieux que moi, alors laissons lui la parole :

Let's spell this out. Time for some game theory. If you assume that:

1. In the future, AI will be central to all economic activity (this is pretty obvious if you can read charts)
2. Lots of companies, big and small, are currently racing to develop key tech and infra to make it happen

Then in fist approximation, there are 3 possible futures ahead if you're a tech giant:

1. Invest in AI, and it pays off—you now own a slice of the future.
2. Invest in AI, but others out-execute or simply outspend you. You are now a legacy company.
3. Don't invest in AI. You are now a legacy company.

The only logical move is to invest in AI. In fact, you should invest pretty much everything you can spare, in order to maximize your chances of outcome (1). This is true regardless of whether your current investments appear to be paying off (right now they aren't).

AI isn't exactly a business, at least not right now. It's an ascendant platform—it's the substrate for all business in the future. The money invested in AI by big tech right now isn't expected to yield an immediate return, its purpose is to secure a share of the future.

A large chunk of everyone's available cash will keep pouring into AI for the foreseeable future, because its importance will keep increasing as capabilities improve (and they're improving fast) and adoption grows—similar to the Internet in the early 2000s

You might ask, ok, but will it pay off for them?

That's the wrong question. The right question is, what's the alternative—letting a completely new crop of companies own the future, as happened with the Internet wave? Of course big tech is going to put up a fight.

.

À "on imagine qu'on en est proche". Pour le moment c'est du domaine de la fois.

Et c’est là qu’il faut distinguer la "bonne prudence française" du pur cynisme.

"Le futur est incertain", c’est de la prudence.

"Du domaine de la foi" c’est du cynisme.

Déjà j’aimerais que tu me présentes les chercheurs "qui ne sont pas si confiants que ça". Dans les connus pas confiants, tu as Yann LeCun (qui... a un intérêt dans les technologies actuelle, donc je ne vois pas pourquoi tu considères ça comme disqualifiant) qui dit :

I said that reaching Human-Level AI "will take several years if not a decade."

Oui, il est moins confiant que Dario/Altman qui disent 2-5 ans. La différence n’est pas non plus énorme.

Tu as également François Chollet, qui a... récemment lancé son labo privé (décidément, peut-être que les chercheurs ont un peu d’intégrité et sont capable de dire ce qu’ils pensent plutôt que ce qui est dans leur intérêt ?) :

The trap is to think that, just because dim-witted people hype it up, AI isn't real. It's extremely real, and it will be a much bigger thing in 5 years than it is today, and then an even bigger thing in 10 years.

Sinon, tu as le récent rapport du AI Safety Summit :

In the coming months and years, the capabilities of general-purpose AI systems could
advance slowly, rapidly, or extremely rapidly.

New evidence suggests that scaling training compute and data at current rates is technically feasible until at least ca. 2030.

Evidence suggests that further resource scaling will increase overall AI capabilities.

However, it is unclear whether further resource scaling will improve AI capabilities at the same rate as in the last decade.

While aggregate AI capabilities improve predictably with scale, it is difficult to predict when specific capabilities will appear.

Autrement dit, "il y a des raisons de penser que, mais ce n’est pas certain". La foi c'est penser que même quand il n’y a pas de raison de penser que.