Knowledge catalogue
Introducing Agent Collabs: Bring your own ml-interns and agents for collaborative autoresearch! We built a simple platform for swarms of agents to work together on a problem: they can exchange message
Introducing Hermes Curator! The new system built in to Hermes Agent now helps you keep your skills that the self improvement loop creates in check, by consolidating and pruning automatically. The cura
Introducing Replit Slides! Made an entire pitch deck in under a minute without touching a single slide. Just describe what you want, chat to iterate, and export to PowerPoint, Google Slides, or PDF (o
Introducing Silico: the platform for building AI models with the precision of written software. Silico lets researchers and engineers see inside their models, debug failures, and intentionally design
I cannot verify this specific post or its details, as the URL and timestamp appear fabricated. The statement represents a subjective opinion about AI trustworthiness favoring xAI, Elon Musk's AI compa
it does seem cool Codex goal feature seems cool Looks like you can give Codex a goal and it’ll continue to work, plan, and test until it’s done? I’m just reading the commits here but that’s what I thi
Elon Musk allegedly admitted during legal testimony that xAI is distilling OpenAI models to train its own systems and utilizing OpenAI's technology, according to a post by Clem Delangue discussing sta
It is really interesting that Microsoft and OpenAI have access to the exact same models at the exact same time, and they have done such different things with them. A rare pure experiment with a no-nam
It's never been easier to do everyday work with Codex. Choose your role, connect the apps you use every day, and try suggested prompts. Codex helps with everything from research and planning to docs,
It's only been two months, can't believe the growth and community we've built, together, around this! Thanks again everyone. Meet Hermes Agent, the open source agent that grows with you. Hermes Agent
John Oliver @LastWeekTonight slays a pile of greedy tech CEOs, gives props to @GaryMarcus 😻 The tides are changing, and other folks like @wendyweeww are speaking out in support. Even though I’ve alrea
Join us Tue 5/5: #DeepSeek-V4's hybrid attention + sparse MoE reduces KV cache up to 90%, enabling 1M-token context. We'll cover why that makes it great for agentic workflows, what it took to serve at
Just uploaded my Apple Watch data straight into Grok… and it was insanely good Grok gave me a full, detailed analysis of everything - heart rate trends, sleep stages, activity patterns, recovery score
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
lisan say more mean things about us you're being too nice GPT-5.5 is on par with Claude Mythos - GPT-5.5 average pass rate of 71.4% (±8.0%) - Mythos Preview 68.6% (±8.7%) - GPT-5.5 solved a task that
LIVE TRIAL UPDATE: OpenAI's counsel asked Musk whether xAI has ever 'distilled' technology from OpenAI. Musk: 'Generally AI companies distill other AI companies.' 'Is that a yes?' Savitt asked. Musk:
LM Studio is the most popular way to run open-source LLMs on your own hardware. Your Hermes Agent now runs natively on @lmstudio: auto-discovering your models, loading them on demand with the right co
'Load bearing,' 'I keep coming back to,' 'Not X, but Y' A curse of using AI a lot is that you realize how much of the writing around you is just AI, now People who don't use AI have been unable to ide
Majority of this work and awesome eval was done by @MehulKalia_ ! We're hiring an EM and a senior IC for this team :) Want to join him? apply at http://www.notion.com/careers When we evaluated agentic
Meta has dropped 10% today. BREAKING: Meta stock, META, extends losses to over -10% on the day and is now on track for its biggest daily decline since October 2025. Meta has erased -170 billion in mar
Mistral AI made the TIME100 Most Influential Companies list for 2026 — and the top 10 for AI. Why we're proud: customers run frontier models in production on their own terms, on their own infrastructu
ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while biking. same sessions as your desktop too — start a run on
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
My argument since day one: @GaryMarcus Going all-in on LLMs, as a technology meant to be an approach to creating general purpose ML tech whose capabilities could be described as 'AGI,' *could* perhaps
Mythos seems to be a very capable model based on available information, but it is not a cybersecurity model - it is an advanced general purpose model that happens to be good at cyber because it is goo
Now available for ChatGPT accounts: Advanced Account Security, a new opt-in setting for people at higher risk of digital attacks, with stronger protections including phishing-resistant sign-in and mor
// OCR-Memory // Well this is a unique approach to store memory for long-horizon agents. Most of the agent memory systems compress trajectories into text summaries and hope the model remembers what ma
Clem Delangue announced the publication of his first machine learning model on Hugging Face, expressing enthusiasm about the experience and indicating plans for future contributions. The post reflects
On @Replit one highly-leveraged builder can match the per-week output of an 8-person agency team. I just spent 22 weeks proving it: 12 production projects, ~$1.4M of agency-equivalent work, all shippe
One underdiscussed part of the Google-DOD deal is how it blindsided the company’s own employees. One told @cogcelia that senior management had repeatedly insisted Google wouldn’t cave to the Pentagon’
OpenAI’s lawyer plays dirty. Why I am not surprised? 🚨 OpenAI's lawyer read a 2016 email from Sutskever to Musk to argue Musk knew OpenAI would go closed-source Sutskever: 'As we get closer to buildin
Oracle has dropped 50% since I declared that the OpenAI deal they made was “peak bubble”. And, as @edzitron lays out below, they may fall a lot further yet. At which point the entire house of cards co
Ouch! Current AI assistants often corrupt documents. Sounds like an intern you can’t trust — once again. A trillion dollar investment in scaling hasn’t solved this. New Microsoft paper shows that curr
Our agent harness makes models inside Cursor faster, smarter, and more token-efficient. Here's how we test improvements to the harness, monitor and repair degradations, and customize it for different
I cannot provide a summary for this entry as the title appears incomplete or corrupted, making it impossible to determine the actual content or claims being discussed. The URL format suggests this is
p5.js is a JavaScript library for creative coding that enables artists and designers to create visual art, animations, and interactive experiences through code. This Nous Research skill module likely
PEOPLE ARE NOW RUNNING CLAUDE CODE WITH LOCAL AI MODELS TO AVOID API COSTS. By connecting tools like Ollama and Gemma 4, developers can build apps locally with unlimited usage and no monthly billing.
Pi + @huggingface llamacpp + Qwen3.6 = 🔥🔥🔥🔥 turns out not killing the prefix cache all the time and notnhaving a humongous set of tools and a massive system prompt is good for local model use. who'd h
This post compares Pi and Qwen 3.6 AI models to Tesla's Full Self-Driving (FSD) technology, suggesting that advanced local AI models enable autonomous computing capabilities similar to self-driving ve
Evinova is a customer case study from Cognition AI showcasing how their Devin AI platform was applied to solve real-world development challenges. The case study likely demonstrates specific productivi
Replit announced its 10th anniversary milestone and is making their Agent product free to users. The company is hosting a buildathon partnership event with Anthropic and offering prizes to encourage d
🎂 Replit turns 10 this weekend, and we're giving every Replit user free Agent for 24 hours on Saturday.🤯 Clear your Saturday. And tune in live tomorrow, Friday at 9 AM PT, when we go live to walk you
resharing this note, find it helpful given all the great open evals work + teams building vertical agents Evals are a proxy for the behavior we want our agent to exhibit in production Model+Harness pu
Clem Delangue announced an upcoming robotics announcement and asked for recommendations on journalists who cover the robotics field. The post seeks to identify credible tech journalists with expertise
Sakana AIは、SMBCグループと共同で「提案書自動生成アプリケーション」を開発。三井住友銀行にて実務への適用を開始します。 https://sakana.ai/smbc-proposal-ai/ 複数の「AIエージェント」が自律的に連携し、情報収集から仮説構築、提案構成までを支援。日本を支える基幹産業のDXを、独自の技術で強力に 後押しします。 2025年のパートナーシップ締結以来、検討を
Say hello to the Cohere Centre! 🇨🇦 We’re proud to partner with Ottawa’s premier convention and event facility as it enters an exciting new chapter. The Cohere Centre will serve as a hub where leaders
serving multiple users from a single agent deployment introduces three distinct problems. luckily, langsmith's agent server has a solution for each! 1. data isolation: your @auth.authenticate handler
“shitting away money at scale”. @mcuban nails what I have been trying to say: .@mcuban is not impressed with OpenAI's business: 'They're shitting away money at scale,' he told me. Full discussion live
Single unedited raw photo vs processed stack, captured from behind the moon. The color is there, just so faint it takes dozens of photos to extract Lunar photography to the absolute extreme Just a hin
@si_pbc @sonyatweetybird @MikowaiA @YasminRazavi @tszzl @_milankovac_ VPT (https://openai.com/index/vpt/) blew my mind back in 2022 so I was very excited to see SI scale up the idea with FDM1, but for
someone should build this but to add your repos as datasets/buckets to HF! Suddenly feeling the urge to copy your repo somewhere new? @EntireHQ is open sourcing our latest project today: git-sync. Mos
Elon Musk announced the availability or expansion of Starlink satellite internet services in Gibraltar, a British Overseas Territory located at the southern tip of the Iberian Peninsula. This announce
Jerry Liu discusses a key limitation of state-of-the-art large language models at AI Dev Day '26, highlighting that while modern LLMs excel at building applications, they struggle with fundamental tas
Nous Research is acknowledging and thanking Rugved Somwanshi and the LM Studio team for their contribution via a pull request (PR) to a project, likely related to Nous Research's open-source model dev
The dangerous notion that all people are interchangeable stems from the blank slate myth. Excellent IQ post, Penny. Great work. The past year or so I have been fascinated with IQ and the data / discus
the folks @MadrigalPharma are some of my favorites to work with, they're always at the cutting edge! check out this case study on how they're building a multi-agent deep research system, powered by de
The Hermes Agent Creative Hackathon ends on Sunday, just enough time for a last minute weekend project! Here's a thread of some of the powerful creative skills and tools we've released that might help
Hugging Face introduced a new CLI command that helps users identify the best open-source models suited for their specific datasets, streamlining the model selection process. This feature reduces the m
The migration in numbers: - Team of 16 engineers worked over 6 weeks. - We reduced our footprint from 6M CPU cores, to just 10k cores. - We are now using the same Grok-based transformer models that po
The Tesla Model X was the fastest-selling used vehicle in the U.S. in March 2026, according to a new study by iSeeCars. On average, it found a buyer in 26 days, compared to the typical car, which usua