Knowledge catalogue
Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 198B sparse MoE VLM designed by @StepFun_ai for inference from the start. 196B language backbone with a 1.8B v
nice post from @Harvey and @LangChain Labs, worth a read. improve agent feedback loop without setting $$ on fire Can we design legal agent verifiers that are up to 1,000x cheaper? Verifiers are LLM ju
Lukas Petersson and Axel Backlund of Andon Labs discuss their work on evaluation methods and benchmarking for AI systems, likely covering approaches to assessing AI capabilities and safety in real-wor
We are excited to join Nvidia's Nemotron Coalition of leading AI labs working together to advance open frontier foundation models. To celebrate we have partnered with @nvidia and @nebiustf to provide
A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon
Swyx announces that @jgreze will speak at the ai.engineer/wf gathering, which is positioned as an event bringing together leading agent research labs. The post expresses enthusiasm for the upcoming sp
Stephen Foley / Financial Times: AI will significantly disrupt IT consultancies as AI labs build their own advisory arms and execs expect more outcome-based pricing over hourly billing models — Accent
LangChain Labs is conducting research into developing more efficient verification systems for validating the outputs and work products of AI agents. This research likely focuses on improving the speed
Efficient verification is what makes scaling legal agents practical. Excited to partner with @hwchase17 and the @LangChain Labs team on designing efficient verifiers - sharing early results showing op
This is actually one of the main advantages startups have over frontier labs, as long as there's a healthy spectrum of open-weight to closed-weight models on the cost-performance curve. Building a mod
Many research labs only consider inference efficiency after the fact. Step 3.7 Flash is a 196B MoE model, and built for inference from the start by @StepFun_ai. Multi-Matrix Factorization Attention (M
OpenJarvis: a local-first personal AI is now available to run with Ollama Built by Stanford’s @HazyResearch and Scaling Intelligence labs, as part of their “Intelligence Per Watt” research into effici
10/ The bigger point: your product is the best RL environment you'll ever have. Frontier labs ship models that are good at everything. The opportunity is a model that's great at your thing. Product, u
Someone just asked me “What I don’t get is why you see it as some kind of failure that AI labs are now using harnesses and neurosymbolic tools…?” I don’t! As I argued in my newsletter on Claude Code (
Ha. @demishassabis and @DarioAmodei, who are running the two best AI labs in the world both have PhDs. Jim Simons, who founded one of the biggest hedge funds in the world had a PhD. Eric Schmidt, Goog
Nemotron-Labs Diffusion Language Models represent NVIDIA's approach to achieving faster text generation through diffusion-based architectures, potentially offering significant speed improvements over
And it is the model that makes it so it is the labs, as opposed to every other software vendor, can ultimately be the sole provider of products. Their post-training and their harnesses and their contr
The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, co
As of yesterday, we made everyone within @llama_index research/engineering/product a Member of Technical Staff. Yes all the frontier labs have done this for years. But we didn’t only make these change
Math is easy* because it has verifiable outputs and few messy judgement choices to make. Which AI labs have the guts to make advancing social science a priority? It may actually do more for human flou
Ivan Mehta / TechCrunch: Spotify Labs launches Studio, a NotebookLM-like desktop app to generate private, AI-powered podcasts, in research preview across 20+ markets — One of the common features for c
One interesting side feature of recursive self-improvement, to the extent that is happening, is that it makes the Big Three labs more appealing to talent, and shortens the runway for launching a poten
Reporting from Google I/O 2026 with the four biggest themes from one of the biggest AI labs in the world. 🎤 Voice AI as an interface Google and Samsung announced new Gemini-powered glasses with Gentle
We’re hiring for Labs! 🧪 If you’re interested in working with us to push forward Continual Learning, pls DM me with a blurb + link to the best Applied Research you’ve done (or even better shipped!) yo
We’re releasing Nemotron-Labs-Diffusion - the first Tri-mode LM family (3B/8B/14B) that switches between 1⃣Autoregressive, 2⃣Diffusion, and 3⃣Self-Speculation decoding by simply changing the attention
The first NVIDIA Vera CPUs arrived at three of the world's leading AI labs on Friday — Anthropic in San Francisco, OpenAI in Mission Bay, SpaceXAI in Palo Alto — followed by a delivery to Oracle Cloud
Eleanor Olcott / Financial Times: Developers say Chinese AI labs lead US rivals in video generation, as ByteDance and Kuaishou train models on vast short-form video libraries from their own apps — Chi
Introducing Gemma-4-31B-it-Pearl on Together AI, Pearl Research Labs’ instruction-tuned checkpoint of Gemma 4 31B powered by @prlnet Proof of Useful Work protocol. AI natives can now use this Pearl mo
Dear AI labs, A neverending black and white kanban board modeled after Jira (no offense) is not what we want as the future of work. Give me flexibility. Give me delight. Give me color. Please create t
Nous Research announced that Deepseek V4 Flash is temporarily available for free access through the Nous Portal, courtesy of Nous Research in collaboration with @novita_labs. This limited-time offer p
I was going to say LangChain Labs is the most exciting thing we’ve announced recently, but with so many launches it’s hard to justify… but still incredibly thrilled to see this get started!! Checkout
LangChain Labs is a new applied research initiative announced by LangChain focused on advancing continual learning capabilities. The effort represents the company's commitment to developing systems th
suuuuper excited to be collaborating with the excellent LangChain Labs team on this effort prod agent tracing is the seed that lets you close the loop for continual learning. too much data gets collec
There are some clear exceptions to the rule, but I feel like the labs got the message that they were scaring people and now tweet about happy stuff and random product trash talk rather than the coming
You will know that the AI labs believe in ASI when they disband their newly formed consulting (sorry “forward deployed engineering”) groups. As long as people are required to figure out how AI is usef
𝐅𝐮𝐥𝐥-𝐏𝐚𝐫𝐚𝐦 𝐑𝐋 𝐧𝐨𝐰 𝐚𝐯𝐚𝐢𝐥𝐚𝐛𝐥𝐞 𝐟𝐨𝐫 𝐊𝐢𝐦𝐢 𝐊𝟐.𝟔 You've been told only 3 AI labs matter. The best AI apps never believed that. @cursor_ai, @vercel, @genspark_ai don't run only off-the-shelf models. They trai
Heather Somerville / Wall Street Journal: Execs at Palantir, whose stock is up ~16x since its AI platform's 2023 debut, often decry other AI as slop, as competition from frontier AI labs stiffens — In
Frontier labs are betting AGI models will be so good you won't ever want to customize them. We think different. Building on a closed platform means renting your intelligence. The landlord sets the ter
Labs; “we will have a nation of geniuses in a data center by 2028, capable of beating humans at every task, but you will need to hire our newly trained forward-deployed engineers for a six month engag
Ramp Labs is doing a ton of cool work all the way from launching products to hardcore research on LLM internals, this is a fun one 🔥 Talked to @ramplabs Head of Applied Research Alex Shevchenko on the
Seems like a massively underinvested area in the “pivot to enterprise.” The fact that the Labs are building their own deployment consultancies (which will take a long time) suggests a failure of imagi
Anna Tong / Forbes: Tessera Labs, which uses AI agents to automate enterprise IT migrations and ERP transformations, raised a 60M Series A led by a16z at a 320M valuation — Kabir Nagrecha is tackling
Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Colossus 1. The future of AI runs on
Ethan Mollick advocates for dedicated funding toward developing independent benchmarking systems for AI models, noting that evaluation is currently predominantly conducted by the labs that create the
The unreasonable effectiveness of LLMs is what makes them so weird. The labs don’t need to decide what kind of AI to build, because better LLMs do better at most things. Finance? Pig disease identific
New York Times: Ripple Labs investor and exec Chris Larsen plans to spend 3.5M to help Alex Bores, a NY congressional candidate at the center of a proxy war over AI regulation — Chris Larsen, who hail
This article examines how value in the AI industry is shifting away from traditional chip manufacturers toward model development labs and companies that build large language models. It likely analyzes
I think the expression is “pulling the ladder”! All labs trained their models by distilling (at the very least distilling the web) which allowed them to become the fastest growing businesses in the hi
Distillation is largely an industry standard and not just something done by Chinese labs targeting OpenAI/Anthropic. Many American companies also distill Chinese (open) models. LIVE TRIAL UPDATE: Open
The post highlights a contrasting news cycle where the White House condemned Chinese AI labs for alleged model distillation attacks, while Elon Musk later admitted under oath that his company xAI enga
Most model trainings outside of frontier labs fail. 📈 Because of bad or insufficient data. 🚮 Or just data for what you want + not general capabilities. 🎯 Most builders give up + become elevated prompt
Heather Knight / New York Times: Inside Andon Market, billed as the first retail boutique run by an AI agent; the Andon Labs experiment uses a Claude Sonnet 4.6-based agent to run the boutique — Andon
Raphael Satter / Reuters: Diplomatic cable: US State Department has ordered a global push to bring attention to what it says are efforts by Chinese companies to steal IP from US AI labs — The U.S. Sta
At 30 trillion tokens a day, we're the largest inference provider outside the frontier labs' own APIs. We're hiring. Come build the infrastructure behind the top AI workloads: https://fireworks.ai/car
Nilay Patel / The Verge: Q&A with Canva CEO Melanie Perkins on the company's growth in enterprise, competing with AI labs, token pricing, investing in its own models, and more — Today, I'm talking wit
Iain Martin / Forbes: Mistral, which once aimed for top open models, now leans on being an alternative to Chinese and US labs, says it's on track for $80M in monthly revenue by Dec. — Paris-based Mist
The tensor engine was first implemented inside SN3 (before it was called Lush) in 1992 at Bell Labs by Léon Bottom and me. The naming convention has survived to this day in PyTorch and other libraries
Yohei Nakajima humorously raises a question about the potential conflict of interest and reputational consequences of selling call data from founder pitches to AI labs while continuing to operate as a
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on t
We need a new document that AI labs should release with each new model, besides the model card: a sort of changelog I want to see how & in what way the new model changes, breaks, or improves at a rang