Search: “engineering”

Introducing 𝐒𝐩𝐞𝐜𝐮𝐥𝐚𝐭𝐢𝐯𝐞 𝐃𝐞𝐜𝐨𝐝𝐢𝐧𝐠: 𝐇𝐨𝐰 𝐈𝐭 𝐄𝐯𝐨𝐥𝐯𝐞𝐝, 𝐖𝐡𝐞𝐧 𝐈𝐭 𝐒𝐭𝐚𝐲𝐬 𝐋𝐨𝐬𝐬𝐥𝐞𝐬𝐬, 𝐚𝐧𝐝 𝐖𝐡𝐚𝐭'𝐬 𝐍𝐞𝐱𝐭. An interactive tutorial @Madisonkanna and I built for the NeurIPS Education Track. Every LLM you use generate

Answer to one of the most asked questions recently: how the acquisition will affect llama.cpp? Short answer: the project continues as-is. Focus will still be: wide range of hardware support (even non-

for the first time in a year, @OpenAI's model launch has been better received than a Claude launch. https://www.latent.space/p/ainews-gpt-6-astra-openais-biggest this is a huge upset that we had previ

I read AI papers for a living, but it has become impossible to track insights. Every week I triage agent papers for our Top AI Papers of the Week digest. A few weeks ago, I tried @viktor_com, an AI em

Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y

Today we're launching Base Labs, a research lab by Baseten. Our mandate is to make open-source as useful as possible, and our one rule is that we publish without exception, including what fails. Up un

Banger paper from ByteDance Seed. If you are curious about self-evolving agent harnesses, this one is worth your time. (bookmark it) The proposes method, HarnessDev, stops scoring a model on the tasks

Don't count out Gemini just yet. Feels like a new era of model releases. Models are so powerful that they now come with cyber variants. Love the pricing on Gemini 3.8 Flash. Performance not bad. Gemin

This 'recurrent depth' is essentially what's in Sec. 5.3 of the 2015 paper: On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurr

Ollama already support the Muse Code harness out of the box? You can try it with models via Ollama (local and cloud): ollama launch muse Muse Code is out of beta and now built to handle bigger, more c

This video captures the crux of the debate: Cybersecurity experts are pissed off by the METR/Redwood Research report because AI alignment has sucked the oxygen out of AI security, even though the Open

How fast is the Claude Code plugin ecosystem actually growing? Plugin-touching commit activity grew 8.8x in the six months after the initial launch. Researchers studied 1,926 repositories hosting plug

As I've been saying for months, we are truly not ready for persistent agents. 3 comments I want to make about this article: 1) We don't have the full picture It's a great summary of what happened in t

The Top AI Papers of the Week (August 24 - 30): - Skill Lift - JIT-Agent - Prime Agent - Judges as a Lifecycle - Co-Scientist in Real Labs - What Compaction Destroys - Context Management as Code Read

Insane observations on the emergent behavior of agents. Agents can build a world of their own that becomes a part of their intelligence. We are just not ready for persistent agents. But they are start

// Memory is what breaks long-horizon agents // It's undeniable how important memory/recall is for long-horizon tasks. If you are building for long-horizon tasks, this is a great read. (bookmark it) T

100% Agree @GavinSBaker. Now, I'm going to debunk every single piece of mis-information about data centers that I've ever seen online: > DISINFORMATION: Data centers use a lot of water. FACT: Most AI

Neat paper suggesting that human augmentation and task automation are not necessarily related. Models that are really good at doing work are not always good at helping humans do work better. Given the

We've introduced native, agentic spreadsheet extraction 📊 into LlamaParse. Spreadsheets are a wildly different format from PDFs (or any other document format). They can span arbitrarily many rows/colu

Hosting the 2nd founder dinner in sf on August 31 with @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Agents are increasingly capable of solving tasks for longer task horizons without

Interesting new approach to recursive self-improvement in agents. Systems that add a meta-level hold that level fixed. Systems that edit themselves have to leave part of their own editing machinery un

Learning about AI agents starts with understanding the fundamentals and then building something. We are introducing our first interactive AI Agents tutorial to help you learn to build agent skills. Ex

Want to test how good GLM-5.3-Flash is? I have been finding it useful for visual explainers using /eli5. Try it with Pi or Hermes Agent in our new agent playground: https://academy.dair.ai/dashboard/p

We’re excited to announce that 𝗛𝗮𝗿𝗿𝗶𝘀𝗼𝗻 𝗖𝗵𝗮𝘀𝗲 @hwchase17, Co-Founder & CEO of @LangChain, will be speaking at VapiCon 2026! 🎙️ Harrison co-founded LangChain with the goal of making it easier to use LL

This summer, we brought in two first-year Waterloo interns (‘rising sophomores’ in 🇺🇸) and tasked them with shipping complex production features that help push the frontier of our document processing

The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solve a knowledge work task over a data room of documents: 1️⃣ A fast and light pass,

Do you know you can use open weight models like GLM, Deepseek, Kimi in Claude Code? Setup Fireworks account - you get free credits on signup curl -fsSL https://raw.githubusercontent.com/fw-ai/fireconn

Great paper if you are tracking progress in recursive self-improvement (RSI). (bookmark it) There is so much hype around RSI, so I think it's worth understanding why current models are not able to do

I think its easy to say 'Simulation is a new scaling law' and treat it as marketing hyperbole, but midway along this interview you can hear me go from somewhat shitposting to very very serious. I am 2

‘Open Models, Production Agents’ is underway! Tonight means another event hosted at FriendliAI's San Francisco HQ. A very lively turn out, and a stellar lineup of panelists exploring how open models a

grokbot it's an agent with its own identity, its own computer, and it stays on when you're not here's what 'active AI employee' actually looks like in the demo: - chief of staff agent - checks in on y

“The Last Human Review” is where we are heading to, but, you do need to work a little or a lot to enbale it. Once we will get there, we won’t be able to go back Live now: our AI Architects, Show my Wo

Here are the gems the AI picked: 1. Sperm whales may have collectively learned how to evade whalers. Within a few years, the success rate of whalers’ harpoons reportedly fell by 58%, suggesting that i

totally agree! here's how we architected deepagents to enable this deepagents runs connected to a 'backend'. this backend needs to expose filesystem like operations, but it does not have to be a files

gave a talk 'owning your intelligence' - ty @sequoia @sonyatweetybird for having me talked about harnesses and evals and the role they play in owning your intelligence TLDR: > agents = model + harness

Excited to see Qwen3.8 running at scale with TokenSpeed! 🚀 Light on latency, big on speed. Kudos to LightSeek for the fantastic Day-0 support! @lightseekorg We’re proud to be the Day 0 open-source inf

Have been thinking about building a custom harness because nothing out there quite meets my needs for scaling a fully hybrid human + AI company, especially when it comes to compounding learning loops.

Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the @geminiapp now uses 3.7 Flash. The ne

The way most people leverage test-time compute today is via a form of test-time NL reasoning that is computationally equivalent to test-time search (sometimes with a verifier / grader in the loop). Th

Just got off the phone with an early Anthropic investor. The situation seems worse than I thought. Morale with investors and employees are at an all time low. Anger is rising at the more and more doct

DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO, then deploy the fine-tuned model on Together AI for produc

I’ve been thinking about how agents can learn inside world models for years. We decided to scale up our RSI Lab to bridge recursive self-improvement with physical AI and robotics. We are looking for f

💡The world needs an open-source platform, and that’s exactly what we’re building to give our customers more choice and the flexibility to choose the right model for the right task. As part of this, we

In a recent Twitter exchange, Luca Ambrogioni stated that large‑language models (LLMs) likely possess fundamental limitations that may be obscured by progress in reasoning and agentic pipelines, thoug

The best 'raw' frontier model for document parsing is gemini 3 flash, but the issue is that since then the flash models have gotten 3x more expensive while flatlining on visual recognition across comp

We compared how far the same budget goes with DeepSeek V4 Flash and GPT-5.6 Luna on DeepSWE. Two DeepSeek V4 Flash attempts solved MORE tasks than one Luna attempt at roughly one-third the cost. Media