Search: “applications”

This is what production RL infra looks like. ICYMI: RL training at scale separates into two distinct problems. - Tight collective comms for the trainer. - Distributed async inference for rollout. Kudo

AI obsessions, continued: the act of naming something, whether something is 'earned,' what 'carries' something else, strained metaphors, sitting with something (often an idea), an inanimate concept th

AI+Optimus will enable universal excellent healthcare that is better than anyone receives today Back pain sucks; AI could provide the answer to it. Elon: 'So, if you've got humanoid robots that have v

Boom also had a board meeting where the board told me to shut the company down. XB-1 hadn’t broken the sound barrier yet. The team deployed in the Mojave desert was exhausted from months of fighting t

I have been playing these world models/games since the first diffusion DOOM, and multiplayer at 20 FPS is pretty neat. 'A dream of rocket league,' indeed. Introducing MIRA. A playable, multiplayer wor

Sovereign AI strategies of all types are built on the assumption of continuous releases of open weights models that keep pace with the frontier, giving cost/privacy/control gains at the expense of onl

Ethan Mollick argues that the specific format used for documenting requirements or processes (RFP, PRD, SOP, etc.) is less important than the quality of the content itself, and recommends using whiche

The overwrought language of Fable is an ongoing problem in software and design projects where the AI is otherwise excellent. It just creeps into little bits of text and toasts and menus, even if you t

This is a key reason I don’t expect the flow of frontier open weights models to continue indefinitely, or even for very much longer. https://www.reuters.com/world/beijing-is-looking-curbing-overseas-a

Unsurprising but still big: MTurk is on its way out. Mechanical Turk was a mainstay of social & survey research through the 2010s, as it allowed you to quickly buy access to many representative humans

World models are very interesting. https://x.com/connerruhl/status/2074245101379846400?s=20 Do world models work as a medium for storytelling? Over the weekend, I wanted to see how far I could push re

Yohei Nakajima proposes an alternative model development structure where AI models are created through specialized production teams assembled like film studios, with each team tailored to the specific

amazing how much shit @ylecun used to give me for saying basically this pathological that he won’t acknowledge it During a Bloomberg interview, Yann LeCun (@ylecun ) explains why LLMs are limited in t

Ethan Mollick discusses how token costs for AI systems shouldn't be viewed purely as expenses, arguing that some token usage represents research and development spending to understand AI capabilities,

Anthropic and OpenAI will increasingly be able to serve weaker versions of frontier AI (Haiku, Instant) at very low cost And owning the full range of intelligence means they might provide 'organizatio

As you can tell, we’ve gone all in on building the best in class document understanding service with LlamaParse. If you’re looking to process complex documents in production, come check out LlamaParse

Big gains in PotatoMonetBench from Opus 4.5 to Fable: 'There are two controls. One is slider, in which one side is labelled Maximum Potato and the other is Formalware, there are four positions. The ot

Ethan Mollick discusses Google's potential to develop frontier AI models, suggesting that Google has the capability to compete in advanced AI development if it chooses to re-enter or prioritize this s

I can basically guarantee you are not being ambitious enough with the work you are assigning Fable Start asking for the maximum possible thing to figure out the far edges of what it can do. After that

I talk to a lot of companies that still have active efforts to build GPTs. (It remains weird that OpenAI abandoned GPTs after rolling them out. They were the precursor to Skills & could have been a br

I wonder if Fable might do better at tasks it 'likes' than those that it doesn't. If you ask it to do something 'Fable-y' it reacts with enthusiasm and promises to overdeliver. Otherwise, it just gets

'Most enterprise workflows don't require frontier AI models. Outside of coding, tasks like summarization, document generation, and briefing can often be handled effectively by lower-cost open-source m

Since President Trump's re-election, the vast majority of job growth has been in health care and education. Despite promises to re-shore industry through tariffs, over 100,000 manufacturing jobs have

This post likely discusses how AI-generated responses tend to flatten or diminish the creative, humorous, and unconventional character of unusual or whimsical social media posts. Mollick appears to be

'The frontier labs will keep owning discovery. Open source will increasingly own production.' Insightful take on a tired topic 'When you're running AI agents in production for customer service, latenc

(This isn't some sort of boosterish AI slop post, I really think the right way to use Fable is to start by asking for everything and find the shape of the frontier from there, rather than starting wit

We drove 410% conversion lift on @Replit's enterprise funnel, 2x-ing the number of demo requests. All in a matter of months. 'Coframe makes you feel like you have a team of 100 people. There's nothing

With inference scale and research scale to drive efficiency, and ever-improving frontier models as brains, this would be a way for the Labs to undercut even open weights models. Some companies will st

As working with AI agents looks more like management, we may want to consider large-scale management training for the AI era. The US government actually did this once, & the WW2 Engineering, Science,

One of the most misunderstood facts is that the US was founded with abundance, whereas it was in fact built from scratch. At the time of founding, Britain was the greatest nation governing the Seven S

This post likely discusses how rapidly frontend design trends and 'vibes' evolve in technology, suggesting that design approaches from just six months prior can feel outdated or obsolete in the fast-m

When people discuss China vs. US competition over AI it would help if they specified the grounds of competition because there are divergent beliefs on what the actual game is, or if there is a game at

'History can be written of monsters, and in them,' reads China Miéville's 'Theses on Monsters.' https://conjunctions.com/articles/china-mieville-c59/ as a society we need to invent another classic mon

Ethan Mollick, a prominent AI researcher and entrepreneur, posted commentary on X about poor quality or unhelpful AI bot responses to a particular topic or question. The post likely discusses limitati

We are leaving the Old Code Age, the Paleocodic, the artisinal code era, where if you needed a novel program, you would commission a local codesmith or code guild to hand-craft a work of code for you,

Ethan Mollick reflects on how future generations will be amazed at the complexity and scale of work humans accomplished using only traditional keyboards and interfaces, before presumably more advanced

What if the model is the router? I think people underestimate the ability of frontier models now, but especially in the near future, to delegate work on their own as needed to dumber, cheaper models.

A big part of how the team at Runway is able to build and train the models we do and serve the inference demand we have is that we've built incredibly robust research infrastructure and tooling for al

America needs to build again, and it is building. We kick off our @corememory 4th of July American manufacturing extravaganza with the latest temple to metal built by @elonmusk and the @tesla_semi tea

At Cohere we deploy our models directly to our customers, instead of them sending data to us. It makes our job harder, but their business more secure: “When you’re using a consumer app, they are using

Fable: 'Last and First Men is out of copyright. I want you to make a movie that features a reading of it with appropriate mixes of animation and images using access to the APIs you have (elevenlabs, h

I find projects like this show that yes, Ais obviously have judgement and taste. Maybe not your or my preferences, and maybe not good enough for all uses, but you can’t make all the choices required f

I never touched any tool or anything, all designs & prompts were the AI's choices. I pushed back a couple times: 'Are there ways to make the whole thing better - it is lots of static images and such?

That's a wrap of @aiDotEngineer World's Fair 2026 🥳 Many times larger than in previous years and yet it still felt like an intimate gathering of friends and family, what an incredible production by @s

While it is obviously true that not having verifiable domains makes training models in those spaces difficult... it is also true that models are also getting much better at non-verifiable domains. The

AI implementation advice on my X feed is divided between those who 'feel the exponential' and those whose (unconscious?) mental model of AI is that this is about as good as it is going to get, so it i