Search: “llm”

Yes, open-source / open-weight models are important for a healthy AI ecosystem. That's how we can verify things, check claims, and keep up outside the closed labs. Plus, it gives us the freedom to run

Claude Opus 5 generated an entire game demo from Scratch, with no external assets used—Matt Shumer posted a video of the AI‑created gameplay on Twitter. The clip, narrated by Shumer as “AI games are g

having an event stream like activegraph is the base of how we move to next level and that will probably be composition, which can let you achieve better results with smaller models. - get the core eve

Open weights = freedom. You can run them on your own hardware. No vendor can pull the plug. No API can deprecate you. No company logs your private data. That's sovereignty. Closed models hand one comp

Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it t

Dynamic workflows are a generalization of harnesses, automations, loops, routing, and graphs. It's the most powerful feature I have built into my agent orchestrator. Supports all kinds of patterns tha

Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behavior is often harder than writing the edit. Harness Handbook

Wish Dario had taken this bet. 🎺 I am hereby publicly offering to bet @darioamodei $1,000,000 that AI in 2027 will NOT be “smarter than Nobel Prize winners across most fields in science and engineerin

just watched @yoheinakajima's Active Graph talk at AI Engineer. not a code call graph but the agent run itself is the graph: goals, tasks, evidence, decisions, all projected from an append-only event

New research from Meta. (bookmark it) Most factuality work checks whether the claims in an answer are correct. GAMUT goes after the harder question of whether the answer covers everything it should. I

Domesticated, not feral: Why evolvable AI is not yet a Darwinian threat Writing in PNAS (Proceedings of the National Academy of Sciences), three heavyweights in AI and evolutionary biology criticized

Not because Andrej is saying it but I think voice is goated. And you can mix it with other modalities for even richer prompting. I recorded a session a few weeks back to demo the power of multimodal p

Huge launch from @tryramp. Different steps in an agent workflow can use different models. This can help reduce costs significantly without sacrificing performance. Model routing will become a core par

AI agents are already being used to improve the capabilities of our next-generation models. We believe with GPT-Red that we have started to unlock a similar flywheel for safety, where today's models c

We scaled a robot model natively to 8,000 timesteps of context, 5 minutes worth of muscle memory, with constant inference cost. Robot policies used to live their lives a few frames at a time (< 0.1 se

cosign. models have overtuned to this now and do not realize when the agentsmd is out of date and should be changed/ignored. last night i goaled 5.6 sol to complete a 5 stage task and woke up to find

By the end of the year we should have: GPT 6 Fable 5.5 Gemini 3.5 Pro Grok 5 Spark 2 Kimi 3 Minimax M3.5 GLM 6 DeepSeek v4.5 Mistral 4 Qwen 4 MiMo 3 Never in the history of LLMs has the frontier been

Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without having use CLIs or open the browser? We built exactly that. Using @TauriAp ps, with a Rust backend power

We just shipped a full revamp of the RunAnywhere apps. iOS and Android, live now. One assistant, fully on-device, works offline: - new UI, opens straight into chat - device-aware model recommendations

🚀langchain launches this week: all about open source models and memory! First: open source models. We partnered with @NVIDIAAI to launch a NemoClaw DeepAgents blueprint. This pairs Deep Agents (our op

One of my first journeys in neural networks started over a decade ago with implementing CPPN-NEAT! Back then, I built a clone of ‘Picbreeder’ not only to study the mechanics of neural nets, but to exp

Thanks for the shoutout! Excited to see OpenWiki 0.0.3 launch 🥰 I believe wiki-based memory is a more governable, sustainable, and hierarchical direction for agent memory. Looking forward to continuin

Bigger update coming tmrw, but a bunch of small fixes today! OpenWiki 0.0.3 just launched with tons of bug fixes and improvements! Some notable changes: - 'openai-compatible' provider to support any L

We're continuing to work hard to make OpenWiki better and better! v0.0.3 just launched with a lot of improvements. What do you want to see next? OpenWiki 0.0.3 just launched with tons of bug fixes and

this is a great approach, seeing this more @flymy_ai also does this when you build an agent via their api, they'll build a deterministic reusable workflow, except for where you need models we built th

Check out all the amazing work from our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation (https://www.physicsoflearning.org/) presented at the main meeting of @ICMLconf #ICML

// HASTE: tiered skills for ML engineering agents // Why do ML engineering agents keep rediscovering the same techniques on every new task? Because each competition is a cold start. New research intro

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and le

I've been going to tech conferences since eternity and I have to say @aiDotEngineer is something else every time I go I meet coolest people, we stay in touch and ship cool things together, it eventual

Some notes from @aiDotEngineer world fair: > the energy was incredible. it's magical to have a large group of smart, hungry, technical, and driven people learning from each other under one roof. > the

We are pleased to present our latest research at #ICML2026, “Bridging Spherical Black-Box Optimizers” https://arxiv.org/abs/2606.25761 When optimizing through simulators, external APIs, or in reinforc

// AutoMem // I quite like this idea of metamemory. (bookmark it) This new research from Stanford treats agent's memory management as a trainable skill instead of a fixed module. The model decides wha

Dario just declared war on open-source. Anthropic's message is clear: open source could destroy the entire AI business model, and Chinese open-source models are the cause. I sat down with @jasonlk & @

we built the @hyperspell filesystem around this principle every source in your company feeds into a context graph where we resolve conflicts and assign permissions there’s a filesystem on top of the g

Introducing SWE-Together: a multi-turn benchmark built from real user–agent coding sessions. Coding agents are often benchmarked like exam-takers: given the full spec up front, then graded on the fina

It's wild how quickly Etched designed and got the chips out, all within 2 years. They went deep, hardcoding attention into silicon and getting very high MFU. This kind of hardware tailored made for LL

Qwen publishes new work on RL coding agents. (bookmark it) The idea is to continually build a verification system that co-evolves with AI agents. LLMs suffer from all sorts of reward hacking issues. T

Row-Bot's approach to memory is hybrid. We have taken the best of both worlds. A knowledge graph for the agent + bi-directionaly synced Wiki for human readability/audit. With in-app graph visualizatio

it's never been easier to turn langgraph agents into voice agents! great tutorial on how to do so, featuring @pipecat_ai Turn any LangGraph agent into a voice agent, no rebuilding required. A how-to o

It's quite rational to regulate frontier API models, especially to get more transparency for the government, without regulating open-source AI. Here's why: 1. The most dangerous AI systems right now a

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching. Better Defaults (not Usage Caps) – Engineers can choose

I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab

NEW paper from NVIDIA. (bookmark it) Speed-of-light performance analysis tells you the theoretical floor of a workload, but teams still derive it by hand and freeze it. SOLAR automates the whole thing

Building Agent Skills is great, but testing them clearly and across agents is difficult. The Pinecone DevRel team has released Cultivar, a CLI tool and agent skill designed to solve this problem. With

Crazy how many times people have told me over the last five years that a solution to hallucinations was right around the corner — and yet here we still are. This study tests how often LLMs invent answ

focusing on a single user story in your marketing can be challenging because you feel like that one story might not resonate with all of your target customers but when done well (like this), it’s emot