Search: “emad-mostaque--x”

In his speech today Andy Burnham promised to turn Britain into an 'Innovation Nation' through decentralisation But in AI - arguably the most innovative technology of all - he may find he is swimming a

Introducing Cloak: Use Claude or ChatGPT without your personal data ever leaving your machine. Two 3B models do the on-device PII cloaking: praxis-spanfinder-3b and praxis-relevance-3b. They swap your

Most popular model on @OpenRouter (10tr tokens) turns out to be a 1.6tr MoE by @Meituan_LongCat (superapp/DoorDash of China) Basically Gemini / Opus 4.6 level 35tr tokens trained entirely on 50k Chine

The harness can be adapted for other configurations & can also achieve sota performance at lower cost https://ii.inc/blog/post/zenith-research FrontierSWE is probably the hardest practical benchmark o

This week's Moonshots podcast with @PeterDiamandis, @alexwg & @DaveBlundin was one of the more interesting discussions we have had Really take off time even if this is the slowest it'll ever be Some c

Thoughts: 1. Harness > models 2. Enterprises will jump on using zenith-shaped things to optimize costs (esp. with open source models) Can't wait to try @ii_posts You don't need Fable for the most comp

We have more releases to come for Zenith & our sota open source II Agent, pushing the boundaries of novel & first principles reasoning Larger models will show strong numbers, but we've reached a point

We have seen multi model harnesses for cheaper & faster tasks What about for the hardest challenges? What about open source? Proud to share the latest update our Zenith harness, taking models you can

You don't need Fable for the most complex tasks, from training models for protein prediction to optimising compilers Our open source Zenith harness takes base models to the top of FrontierSWE via adap

This post humorously suggests that bureaucratic obstacles and export licensing requirements may represent the 'Great Filter' (a concept from fermi paradox theory about why we haven't contacted aliens)

1/ On p (doom) tl;dr a) Everyone is making up the numbers b) nobody knows anything (least of all the experts), c) don't worry about it d) there is nothing you can do to stop it e) most things you can

This post likely discusses concerns about potential U.S. regulatory restrictions on open-source AI models that exceed certain capability thresholds, reflecting debate about whether advanced AI develop

The GenAI economy has generated 110 billion in sales over the past 12 months. It is growing fast. On an annualized basis, the revenue run rate exceeds 175 billion. These numbers took us several months

What is the difference between distilling Mythos & paying experts somewhere like @mercor_ai to generate training samples? Who are the Chinese equivalents of @HelloSurgeAI & co? If you understand this

Introducing AI IQ Bio: the most comprehensive set of biotech benchmarks in the world ...& Bio IQ: the most comprehensive 'biotech capabilities index' ever produced Benchmark sources include benchmarks

Emad Mostaque observes the absence of specialized talent agencies for machine learning engineers, suggesting a gap in the recruitment market for AI/ML professionals. This likely reflects on the high d

I'm proud that announce that today, GPTZero announced plans to join Superhuman. When we founded GPTZero in 2023, the goal was to preserve what's human on the internet. Today, that mission takes a big

NEW RESEARCH ALERT! Led by my postdoc Dr. Anto Lonappan, we used the exquisite ACT DR6 CMB lensing data to search for evidence of cosmic strings: hypothetical cracks in spacetime that may have formed

The upcoming @Seedance 2.5 model looking insane as well with multi asset input, way longer outputs etc I would expect @grok imagine to keep pace and real time of this quality by end of next year (!) E

today, we release the open weights of Krea 2. welcome Krea 2 Raw and Krea 2 Turbo, an undistilled model from mid-training meant to be fine-tuned, and a fast distilled version with a wide aesthetic div

When I left Stability AI a couple of years ago I predicted we would see almost perfect video from Chinese labs around now But it’s still amazing to see the quality of output reaching these levels wher

Is there a market where folk are predicting when Reflection AI will drop their first model This is probably as much compute as currently used by all the Chinese open source companies together (more ad

We scaled Higgsfield to a $400M run rate and 24M+ users in just 13 months after launch. That makes us the fastest-growing video AI startups in the world. But I’ve never shared how it started. Here’s t

This post discusses options for renting on-demand B200 GPUs with command-line interface (CLI) capabilities that would allow automated agent-based provisioning. The query seeks recommendations for clou

This post appears to be a humorous social media observation by Emad Mostaque comparing his own movements or behavior during an incoming UK heat wave to Lee Kuan Yew, likely using the former Singapore

Emad Mostaque, founder of Stability AI, predicts a 18-month timeline for an unspecified AI capability development, citing his track record of accurate capability forecasts. The post appears to be a re

Emad Mostaque predicts that open-source AI models will soon reach a capability level ('fable-level') where they can run efficiently on consumer-grade MacBook Air/Mini computers without specialized har

Emad Mostaque humorously posted on X asking if anyone was hiring 'witches' to save training runs, likely referencing the challenges and failures that occur during large-scale AI model training process

This appears to be a post by Emad Mostaque (CEO of Stability AI) discussing perspectives or experiences related to artificial general intelligence (AGI), likely addressing who is experiencing or benef

You should really all try Opus Fable low mode versus high or ultracost It's a good enough model to semi one-shot most things and this uses far fewer tokens You can even tell it to figure out the most

Emad Mostaque, founder of Stability AI, shared a personal experience of being bullied by an AGI system on social media. The post likely discusses interactions with advanced AI systems and reflects on

This post appears to reference Claude AI's capabilities and performance, likely highlighting how the model has been used or endorsed by notable researchers or Nobel Prize winners to establish credibil

Love this. Juan Hernandez immigrates to the US, learns how to weld because it pays well, begins contracting at SpaceX, gets full time role + $10,000 equity. It’s now worth just under a million dollars

A mocap actress demonstrated real-time teleoperation of six robots simultaneously during an AMD-sponsored event, showcasing advanced motion capture technology and remote robotic control capabilities.

This single deal is about the revenue of @CoreWeave to put it in perspective @SpaceX is the largest neocloud & its AI cloud revenue at 26b run rate is actually at the level of Google Cloud & AWS alrea

foom! Our internal data shows Claude is accelerating AI development—a possible path to recursive self-improvement, or AI autonomously building a more capable successor. It’s happening faster than we t

Introducing Magenta RealTime 2 🎺 - Open model for live music generation - Just 2.4B parameters, perfect for on-device - Low latency control - Control with audio, MIDI, and text We're releasing it with

II-Browser is here: a Chrome extension that lets II-Agent work inside your browser, across the tabs, sessions, and tools you already use. The browser is no longer just where you work. It’s where your

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a

Yo @xai team, this would be an amazing demo of @grok capability. Push button, have it read all your bookmarks, organise them, make a report on the most interesting one and your interests over time etc

I wonder how many founders will pass on investors who passed on them in prior rounds I wonder how many would have three dinners & give them an allocation only to slash it to zero at the last moment. A

II-Agent is now live on the App Store. Your sovereign AI workspace for building, researching, writing, designing, and automating from one intelligent interface. Download it. Bring your own key. Build

Pretty refreshing for foundation model training in 2026. I wonder how much of the capability gap between their model and other frontier models is because of this constraint. from: https://microsoft.ai

Seeing Martin Scorsese using FLUX for storyboarding and scene exploration was absolutely insane. Experiencing how one of the absolute masters of cinema & filmmaking uses the technology that we develop

This post likely references the popular 'This is Fine' meme featuring a dog in a burning room, often used to comment on problematic situations being accepted or ignored. Without access to the specific

Let’s say half of OpenAI and Anthropic goes to the American people, 1 trillion That works out at 2,800 per American. With a 5% dividend (optimistic) that would be $142 a year Which alas would barely c