Knowledge catalogue
Transitioning from using a single video model to generate a clip to achieving a finished video is like the transition from coding models that merely autocomplete to coding models that write working so
Update: it's fixed! @simonw @ClaudeDevs @claudeai This is fixed — the egress proxy was incorrectly blocking git/gh reads to public repos that weren't attached to the session. Clones/fetches work again
Gary Marcus discusses concerns about generative AI's limitations and potential overhyping of the technology, arguing that initial enthusiasm may not translate into sustained practical breakthroughs as
Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Characters, our real-time interactive avatar model. We had to fi
“We are going to have a multi-racial nation in Singapore. This is not a Malay nation. This is not a Chinese nation. This is not an Indian nation. Everybody will have his place here, equal: language, c
This post discusses the significant infrastructure changes necessary to support the emerging 'Software Factories' paradigm, suggesting that substantial rebuilding of development and deployment systems
We built LiteParse, the fastest document parsing solution on the planet and made it open source. And it just hit 10k github stars. 🦙 Fast to run. Fast to love. Thanks for building with us. If you have
We exist and work so leftists can rule over us. Our labor and taxes get extracted to build and sustain political clients who deliver power to the left at home and extend its reach abroad. Democrats ex
We just crossed 100M annual run-rate. I know many AI companies are capturing much more $ these days, but still proud of the milestone! Maximizing short-term revenue has never been our priority. In fac
We raised $8m to build self-healing software. In 2026, software moves fast. But monitoring and observability are still manual and slow. @sazabi is a next-generation observability platform for fast-mov
Weird to see this just as the administration is delaying a model for the second time in weeks, apparently without clarity about its criteria. You can’t be pro-growth, pro-innovation, and opaque at all
This X/Twitter broadcast by Clem Delangue (CEO of Hugging Face) likely provides an introduction to running open source AI models locally on personal machines, covering topics such as benefits of local
We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a s
What happens when you shift more of the context layer into the model weights themselves? Engram is building a neolab focused on memory and continual learning. Let’s go @dan_biderman @realJessyLin! Fun
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
When the cost of execution drops, the value of taste, strategy, and architectural vision skyrockets. Previously, you were spending most of your cognitive budget on the micro. Now you are free to focus
When you use Cohere, there are no staggered releases. No sudden disablements. We trust you completely: '[The customer] is in full control. We can't see in, we can't switch it off' - CEO @aidangomez Me
Which countries are we missing? America is now paying foreign aid to 177 countries. And Congress just shipped another $50 billion. It's an odd way to run an empire when Washington's cutting checks to
While everyone’s displacing jobs, we’re creating them. A Hero for every family. @hellotohera’s favorite friend 83 year old Stanley Zareff dropped by our office to learn what being a Hero means and ann
While we eagerly await Fable 5's return, our agentic WebGPU kernel optimization framework kept running. Opus 4.8 picked up where Fable left off, pushing Liquid AI's new LFM2.5 230M to an unbelievable
who wants to help eyal poke holes in this approach to run LLM inference... in browser? Looking for peer reviewers 🧪 Built an LLM inference engine in pure WebGPU/WGSL. Runs in browser and Node, on-devi
Without a doubt: A world running foundation models on a billion robots won't be doing it locally. None of the embedded compute will look like it does today. All of the embedded compute will be wireles
Women are not suitable for dealing with the amount of violence necessary to maintain civilization. This is, again, because women are wired to care for babies with whom 'zero' violence is the correct a
Work at OpenAI is being transformed by agents, in every department. Across our entire company, people are using Codex to do work that is more complex, longer-running, and increasingly cross-functional
wouldn’t it be funny if greed undid OpenAI? 🚨BREAKING: OPENAI IPO DELAYED Altman told everyone OpenAI is worth a TRILLION dollars His own advisors warned him that retail investors aren’t buying it… ga
Nous Research has introduced a feature that allows users to create and hatch their own digital pets within the Hermes platform, with the ability to share these pets with others. This update likely enh
GLM-5.2 achieved token generation speeds of 318 tokens per second, surpassing the previously reported 280 tokens per second benchmark, with indications that further performance improvements are possib
AI21 Labs announced achieving the #1 ranking on DeepResearch Bench II without developing any new agents, suggesting they improved performance through optimization of existing systems or methodology ra
AI21 Labs reports that a leading deep research agent achieved a score of approximately 45 six months prior, after which the research community focused on developing improved agents to surpass this ben
3/3 We took 7 weak agents (ranks 7-13, none scoring >45) from the leaderboard & merged them into 1 report/task. Essentially boosting for deep research. The result: New #1 DRB II TotalScore of 64.38. F
400T tokens is what production adoption looks like. Teams are moving real workloads to open models because they want frontier quality, better tokenomics, and more control over inference. Together AI g
5.2 could be better with more RL ... Deepswe's benchmark results are my own experience. I've used all models, GLM 5.2 ≈ Claude Opus 4.6–4.7. Kimi 2.7 code more like inference optimization. Looking for
This appears to be a brief post or reference to an 8-minute duration, likely related to a video, audio clip, or event duration shared by Elon Musk on X (formerly Twitter). Without access to the specif
A huge moment for open source AI - as token usage skyrockets across orgs, so do concerns over cost & data/vendor lock-in & necessity of a multi-AI strategy Keep an eye on @Lux_Capital portfolio cos @h
Agent memory systems often follow a three-step iterative process: executing the agent to generate traces, analyzing those traces through some evaluation mechanism, and then updating the agent based on
This entry examines research showing a discrepancy between people's stated AI usage and their actual behavior, revealing that many individuals who claim they don't use AI are unknowingly or covertly u
A message to the Republicans in congress and the Trump administration. Please stop treating legal immigration like just another issue to be fine tuned and start treating it like the existential threat
A tangible comparison of GLM performance stacked against Opus 4.8 on web tasks by @nutlope. GLM 5.2 is chattier, but still faster when served by @togethercompute and over 3x cheaper. Announcing GLM Ar
This post highlights that while agent architecture design has become well-established and solved, memory systems remain an unsolved challenge in AI agent development. The tweet references an article b
Agentic coding changes what inference engines need to handle. At AI Engineer World’s Fair, Together AI engineers will lead a hands-on workshop on how inference engines work and what it takes to serve
AI is quickly moving beyond emulating the human mind to predicting an increasingly large percentage of all observations in the world. General world models will become a new foundational infrastructure
Yohei Nakajima proposes that sports organizations should make their data openly accessible through Model Context Protocol (MCP) to enable broader public creation of visualizations and data analyses. T
an agent’s gotta dream! just like we consolidate learnings during sleep, agents can learn across runs! 🧠LangSmith Engine as Sleep Time Compute Memory for agents is often described as “sleep time compu
Announcing GLM Arena! A series of tests (infographics, svgs, sites, ect..) ran on GLM 5.2 and Opus 4.8, with prompts included. On average, GLM 5.2 produced 2x the tokens but was still faster + 3x chea
Asmongold explains Keir Starmer's resignation using a WoW raid strategy and it makes perfect sense 'Labour just performed a tank swap. Starmer had too many debuffs so they pulled him out and brought i
At Hugging Face we've been building our own agent that we use via Slack (Moon Bot). Honestly, building your own is quite simple and you'll be happy you did: any model you want (self-hosted if needed),
awesome launch We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 queries in our first fe
Big Tech's 1 trillion AI moat just got DESTROYED by a free Chinese download. Microsoft, Amazon, Google, and Meta are pouring fortunes into chips and data centers because they have been told that whoev
I cannot provide an accurate summary of this entry as the title appears incomplete and the URL/source information seems corrupted or mismatched (the handle doesn't match the URL). To create a reliable
btw Zai IPO'ed in Jan at HK$120 a share. when I first met @louszbd nobody really knew anyone using GLM's. now they have beat deepseek with the world's undisputed top open model and in some respects (s
This post discusses developing a GitLab nodes adapter to enable Hugging Face model storage on decentralized git infrastructure, leveraging open-source platforms for distributed model repository hostin
Changing all our pitch decks to quality, quality, quality cc @jerryjliu0 quality has a quality all its own it's interesting they didn't put arrow from compute cloud to best researchers. Because it def
Claude Code for web just started saying 'GitHub is blocked by egress policy', which is a big problem for me because most of my prompts there start with things like 'clone simonw/sqlite-utils to /tmp t
COMPANY BUILT ON IP THEFT RAGES AGAINST THEFT OF ITS OWN IP ANTHROPIC ACCUSED ALIBABA OF UNAUTHORIZED ACCESS TO ITS AI MODELS, OUTLINING ITS ALLEGATIONS IN LETTERS SENT TO U.S. SENATORS AND THE WHITE
congrats to our friends at Unify!!!! We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 q
Creator seungho__yeo ( IG ) built an entire anime-inspired 2D motion sequence - storyboard to final render inside Comfy. seungho__yeo created this workflow while creator whatzuwant ( IG ) created the
.@cristianoamon and @ClementDelangue drop a 'one more thing' at @Qualcomm investor day: Qualcomm and @huggingface partner to bring open models to Qualcomm platforms and beyond. - Users will be able to
// Critique of the Agent Model // Finally, a paper that tries to define what an agent is and what agency consists of. Good read overall. (great bookmark) The word agent now covers everything from a fo
Decisions about how to use AI in your organization are increasingly organizational design and strategy decisions, not IT choices: How do you integrate agents into your firm? What intelligence will you
Democrats have reached such an extreme that they’re electing someone to Congress who straight up wants to 'eradicate' America. And not only does she believe this but she founded an activist organizati