All entries

Nous Research's Hermes agent framework combines a language model's contextual reasoning capabilities ('this') with an autonomous agent built on their Hermes model series, enabling tool use, multi-step

Harrison Chase, co-founder of LangChain, shared a post emphasizing the critical importance of the 'harness' in AI agent systems, arguing that the harness essentially functions as the agent's memory an

This isn't the only result. As of April 11, agents have set 11 new SOTA results on open problems including: → Erdős minimum overlap problem → Second autocorrelation inequality → Tammes problem (n=50)

This post completely misses the point of @sarahwooders 's original article. The whole point is that memory == context engineering, so it can't be a 'thin conductor'. Saying 'memory is just markdown' t

TIL @cognition usage has ~DOUBLED globally since these 2 launches. people are finding all sorts of creative usecases when u can compose agents together and make them proactive. agent recursion is all

Tired of winning “Americans die of treatable conditions at nearly twice the rate as Spaniards, French, Japanese and Australians,” but Trump wants to divert huge sums from healthcare to vastly increase

Trending well! We're glad the traces are useful to the @NousResearch Hermes Agent community. A third batch is in progress. Very cool open-source traces from @TheZachMueller @LambdaAPI: https://hugging

Try it immediately on Ollama's cloud: ollama run gemma4:31b-cloud Try it with OpenClaw: ollama launch openclaw --model gemma4:31b-cloud Try it with Claude Code: ollama launch claude --model gemma4:31b

Very interesting evaluation from the UK’s AI Security Institute of the not yet publicly available Claude Mythos Preview. On the happy side, in its current form, Myth is nowhere near as scary as Tom Fr

Violence is not the answer. But maybe boycotts are? 🚨 NOW: The FBI is RAIDING the home of a 20-year-old man who threw a molotov cocktail at the home of OpenAI CEO Sam Altman Over a DOZEN federal agent

Ollama posted a status update on X (formerly Twitter) acknowledging that their cloud infrastructure was experiencing scaling challenges, requiring overnight work by their team. Users may have encounte

Boris Cherny and colleagues conducted cybersecurity evaluations of Claude Mythos Preview, finding it to be the first AI model to successfully complete an AISI (AI Safety Institute) cyber range end-to-

We just OCR'd 27,000 arxiv papers into Markdown using an open 5B model, 16 parallel HF Jobs on L40S GPUs, and a mounted bucket. Total cost: $850 Total time: ~29 hours Jobs that crashed: 0 This now pow

Chandra-OCR-2 is an optical character recognition model developed by DataLab, available on Hugging Face at datalab-to/chandra-ocr-2. The model was highlighted by Hugging Face CEO Clément Delangue, wit

Well said The distinction between engineering and magic is entirely a modern linguistic conceit. To the ancients, a wizard, a magus, a sorceror, was not a man who commanded forces outside the laws of

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark t

We've also made improvements to performance, including an 87% reduction in dropped frames when streaming large file edits. We are continuing to invest in making Cursor faster and more reliable. See ev

Google's Gemini Live has been integrated into the Reachy Mini robot's conversation application through a partnership between Hugging Face, Pollen Robotics, and Google. This collaboration brings advanc

We've shipped several quality-of-life improvements to Cursor 3. They bring a little more delight when you are orchestrating agents. Just like in your terminal, you can now split agents for multi-taski

What happened to all the Tesla killers that legacy press and hedge fund short sellers predicted were coming? 🤔 Tesla alone sold 117,300 EVs in the US — more than ALL other EV makers combined (99,099).

when you take agents to production, you need to think about guardrails we provide 2 abstractions for guardrails 1. middleware provides hooks around the agent loop that you can use to handle retries, e

⚡️ with @staysaasy, our second anonymous pod ever: https://www.youtube.com/watch?v=5KnCKadxSPY A conversation with the Stay Sassy duo on how AI is changing software teams, management, internal tooling

Cursor has added file include/exclude filter functionality to its workspace search feature, allowing users to narrow or broaden search results by specifying which files or file types to include or exc

A post by Swyx (AI Engineer) on X (Twitter) expressing gratitude for a shoutout related to Coachella, likely in the context of AI engineering or developer community recognition. The post suggests Swyx

yessssss look at this beautiful portfolio monitoring solution that just sits on top of existing data (CRM, notes, email, calendar) - normalizes revenue to annualized rate - tracks time since each data

You can now host your Replit apps globally - Compute + storage colocated automatically - Enterprise teams can enforce org-wide region policies - New Europe, Asia, South America and Australia regions.

Your AI isn't failing because of 'bad chunking.' 🛑 It’s failing because of a vibe mentality. Our Head of DevRel @RoieSchwabco explains why anecdotal testing is the #1 roadblock for AI devs: ✅ Determin

Harrison Chase, co-founder of LangChain, endorsed the perspective that memory in AI agents is fundamentally a form of context, emphasizing that effective context management is the core requirement for

5 years ago, my little girl was secretly being groomed and transitioned at her public school. 4 years ago, she was still lost in a dark cloud, suicidal, identifying as a “boy” named Toby. Last night,

A very interesting observation by Elon below. And it’s just one example. Startups have brought more progress to the world this century than any NGO or government program. By far. When you hear NGO, th

“Above the api line” Good phrase GBrain is my attempt to be in control of my own personal AI that could become my intentionally designed cognitive armor Open source open prompts means you aren’t under

According to Waymo's published data, their technology is preventing injuries & deaths. My view is that if this is true, and I have yet to see a debunking of their data, then we safety advocates should

'Affirmative action is racism under new management.' - Thomas Sowell South Africa won’t allow Starlink to be licensed, even though I was BORN THERE, simply because I am not Black! We were offered many

After seeing that Claude Mythos marketing turned out to be, as expected, a scam, I wanted to make a master list of tricks being used to market LLMs. The master list includes statements directly from l

Agent harnesses dominate agent building and tie intimately to memory. Closed harnesses behind proprietary APIs force yielding control of agent memory to third parties. Memory enables sticky, personali

AI Dev 26 brings the builders together. We'll be among them. Meet us there 👇 @DeepLearningAI @AndrewYNg 3,000+ developers. Two days. AI Dev 26 x San Francisco is where the people building AI come toge

Harrison Chase, co-founder of LangChain, shared or engaged with commentary emphasizing the importance of owning your own memory harness in AI applications rather than relying on third-party API-based

And if you are interested in the answer, Claude and ChatGPT 5.4 Pro think running OpenClaw with local inference on your Mac uses more total power. Gemini doesn't think so (but appears to have not thou

As should all countries. Bravo. Restore Britain will end all foreign language translation in the public sector, saving hundreds and hundreds of millions. If you live in our country, you speak our lang

Elon Musk posted content on X (formerly Twitter) claiming to highlight hypocrisy in Bernie Sanders's public statements or positions, using Sanders's own social media posts as evidence. The post appear

Elon Musk shared a post on X (formerly Twitter) referencing 'boring away,' likely relating to The Boring Company, his tunnel infrastructure venture focused on constructing underground transportation n

brb trying this now Tax season is here and a connector is all it takes to make @claudeai way more useful. Checkout what we just shipped: Connect TurboTax or Aiwyn Tax (formerly Column Tax) to Claude t

This post from X (formerly Twitter) appears to depict a political demonstration in Ireland framed in strongly partisan terms, characterizing protesters as 'patriots' opposing the Irish government. The

Nous Research's MacbethAI shared a post about creative coding, likely showcasing or discussing generative art, algorithmic design, or experimental programming techniques. The content probably highligh

Currently, ChatGPT has the best way of viewing thinking traces, a short summary of steps in the main window, and a detailed audit in the sidebar if you want it Claude does almost as well, but more sum

Cybertruck is an APC from the future Today I spent 7 hours relaxing to music in my indestructible high performance all terrain luxury robot APC while the earth put on a show of landscapes, downpours,