All entries

deepagents just hit 30k stars on github! deepagents is great for building agents that do complex work. they manage context well and use a durable runtime. though inspired by coding agent design, deepa

🚨 Elon Musk agrees with 'some of the things Anthropic has said' and warns against 'torturing superintelligence' after reading Grok's internal reasoning traces during reinforcement learning “It feels l

Mistral AI demonstrated a tooling solution for engineering drawings that employs the **Mistral Large** model across **four zoom levels**, automatically inspecting and verifying plan details until an e

Fun addition to transformers serve: you can now turn any of the 250 LLM & VLM model into a JEV-like decision model. /v1/systemone scores a set of decision with the model's logits. No need to generate

Ha gave this take to our team last week Will share some (very basic) stuff I vibe coded around this shortly Lots to be explored here! One of my more controversial bets: the AI feed will be the form fa

History never repeats itself but it often rhymes Hint: Transformer rhymes with Diffusion Transformer We were able to fine tune an open weight model (Qwen3.5-9B) on proprietary internal data at @coinba

i don’t know whether this is a joke or serious but the whole challenge with generative AI is that it literally cannot be trusted to follow “simple, generalizable instructions”. the inability of most p

I turned @googlegemma EmbeddingGemma 2, an embedding model, into a speech-to-text model, and it turned out to be one of the fastest STT models you can run on device. On a base M3 MacBook Air it transc

If you’re a researcher, please consider sharing your RL environments openly! Something you built for one experiment could help the entire field move forward. I know we’re in dark days for sharing from

Introducing QwenGyre, bringing elastic RL to extreme-long-horizon (XLong) agent training. ✨ It launches with two core designs: 🥳 - Elastic Scheduler: reallocates GPUs between rollout & training as dem

Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us

Mistral AI announced its Le Chonk model, which performs visual grounding by accurately locating objects within images. On the Dense 200 benchmark it achieved a 42 % score, outperforming even frontier‑

🇫🇷 Le Chonk joins the sudo L7 leaderboard 🇫🇷 We just added @MistralAI's Mistral Large 4 to sudo L7, our benchmark for staff-level software engineering. Mistral Large 4 scores 13.3%, ahead of Muse Spar

The blog post “Multi‑Agent Self‑Supervision: Recursive self‑improvement through collective intelligence” by @hardmaru describes how multiple AI agents can jointly supervise and refine each other’s lea

Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos

New paper from Microsoft and colleagues on generating enterprise data for agents. If you train or evaluate agents on long-running business work, it's worth your time. (bookmark it) MiniCorp is an offi

On October 12, 2026, Gary Marcus (@GaryMarcus) posted on Twitter saying, “No Generative AI. Just one gorgeous building, beautiful light, and an Phone 16 Pro.” The tweet, timestamped 7:01 AM UTC, recei

Open standards are the foundation for AI factories that can scale from megawatts to gigawatts. At #OCPSummit26, we contributed the NVIDIA Vera Rubin NVL72 rack and compute tray designs to @OpenCompute

Over the last few months at @river_ai_inc we’ve developed what we believe is the best system in the world for building your own internal custom models, driven by 10 years of experience training top mo

separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly

Sure does look like @GavinSBaker is “suggesting that public companies are materially inflating their remaining performance obligations”. yet another way the Ai industry is trying to con retail investo

The Bitter Lesson for harness design and formal math! Instead of hand-designing how an AI should prove (decompose, plan, assign agents), what if we just give a frontier model good Lean feedback and le

The Microduck Arena is live! Train your duck with RL, publish it on @huggingface, and race it in the 2 m Sprint, Hill Climb, Roller Sprint and MicroDuck Got a Talent. No robot required. Join the live

This is how we built the filesystem behind Perplexity Projects as a Git forge for agents. Each agent works in its own sandbox and commits to a shared repository where people and other agents can build

Three events, one award, a very respectable 4th place in hot sauce. Our SF Tech Week: → AI Demo Night w/ @ClickHouse + @artie_labs: @imaanxsultan won best demo → @matissemlk took 4th in the Blazel hot

Mistral AI outlines its vision for engineering, manufacturing, and earth observation by demonstrating how the model can inspect mechanical components, extract evidence from PDFs, and analyze gigapixel

We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those

With only ~$1,000 of training compute, we trained 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 a 1.7B coding agent that beats Claude 3 Opus and GPT-4o on SWE-bench Verified 🤯 At 25.5% pass@1, it sets a new record for nanoswe, our op

world’s first full length workshop on claude flows @cjav_dev and Harrison Stall are kicking off @aidotengineer bright and early on a monday morning to a PACKED room, standing room only #AIEngineerNY @

worth noting the trend here --> @harvey post-trained an open weight model for legal work + now @coinbase for fraud narrow task + proprietary data + open weights seems to beat frontier on cost & speed

Zai recently launched a domain‑specific language model called **GLM Legal**. According to a tweet posted at 4:13 PM on Oct 12, 2026, GLM Legal became the leading open‑weight model on both **Harvey’s L

A good example of why open weight and open source models are important - they permit users to fine-tune specific use cases with greater cost efficiency. As has been the case in other technology market

Anatomy skill for building wireframe designs and interactive prototype machines is now an officially integrated optional skill in Hermes Agent You can find it in the optional built in skills in the sk

Decision 3.0 now on Core ML 🍎 d3-lite triaging 1,000 pull requests into vllm-sr workgroups, live on an M5 Pro: 0.12 s per PR, 8.3 PRs/s, nothing leaves the Mac ⚡ lite, nano and mini are all converted

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

Kemi posted on October 11, 2026 from San Francisco about attending events during SF Tech Week, highlighting the Agent Economy Gala where she praised @imaanxsultan and @llama_index. She noted a “silico

Impressive by @river_ai_inc to beat @deepseek_ai rates - cache in particular is tough! Talented team there, full RL + inference stack should be real competition River Inference is live! We're serving

Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev Decision Index boards in our evaluation, on a new Pareto front

Introducing Multi-Agent Self-Supervision (MASS): Recursive self-improvement through collective intelligence Blog: https://pub.sakana.ai/mass/ As AI systems tackle increasingly open-ended research prob

On October 11 2026 François Chollet announced that he has been experimenting with large‑language‑model post‑training techniques using KerasHub, JAX, and TPUs. He indicated that portions of his work ma

Lee Corso would call schools to talk to folks and learn a few things about their teams when they were going to be included in GameDay conversation. ‘College GameDay’ analysts called out over lack of c

🧭 New model: Typed Decision, built on EmbeddingGemma 2 Give it a state + any schema of questions → typed, calibrated answers (choice · score · noul). No text generation, no output parsing. 76.4% on ty

New paper from the team at Sakana AI: Recursive Self-Improvement through Multi-Agent Self-Supervision (MASS) How do we keep improving AI when the tasks become too complex for humans to reliably evalua

Not to get too annoying about it but its worth noting that many of the 5,000 people at the labs with access to advanced model still haven't used them to their full extent: its all cybersecurity & math

One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor intensive process done with human supervision. Now frontier mod

On October 11, 2026 Mina Kimes tweeted that the NFC East had earned zero wins for the week because the division’s only two games were a head‑to‑head matchup that produced no divisional victories, illu