Search: “context”

“We believe in intelligence as a public good before everything else.” Here’s my new episode with @karan4d, who co-founded @NousResearch and helped build Hermes, the #1 personal agent and AI app on Ope

DeepSeek-V4-Flash-0731 is live on Fireworks, day-zero. DeepSeek reports it beats V4 Pro across all 9 agentic evals, incl. 82.7% on Terminal Bench. Better cost-per-task than V4 Pro, at the economical p

Interesting data from the OpenRouter Kimi K3 dashboard: @togethercompute offers one of the lowest prices for @Kimi_Moonshot K3 while also achieving one of the highest prompt cache hit rates. Low prici

Introducing the Parse Gateway There's been an explosion of interest in model routing - you don't always need the best model for every task. That is especially true for document parsing 📄🔀: - Some page

Just for reference, from what I observed in my Using Local Coding Agents blog article last month: https://x.com/rasbt/status/2070518167399698490?s=20 'I tried to analyze why Claude Code uses more toke

Yesterday I cohosted a dinner with @dexhorthy with a wonderful group of founders, to talk about agent loops and loop engineering. Some interesting insights: * Most of our group was *not* actively usin

Model + harness. We have barely begun to understand the best ways to do harness engineering. A huge amount of untapped potential even without models getting better (but models are getting better) Turn

Super interesting new work from NVIDIA. (bookmark it) They suggest building agents as Python objects. Very cool idea and I think it could a lot with agent reliability. More below: Agent development to

We quietly released the open-source Codex Security CLI, but Hacker News found it before we had a chance to share it here... You can now use it to scan repositories, track findings across runs, verify

Everything you need to know about Kimi K3 with @Kimi_Moonshot and @togethercompute team. If you're looking into evaling and building with Kimi K3 I would not miss this one! Kimi K3 has everyone’s atte

Kimi K3 has everyone’s attention. On July 30, hear @Kimi_Moonshot's Feihu Tang explain the architecture and decisions behind it. He joins Jue Wang and Zain Hasan from Together AI for a deep dive into

Are agent skills always worth using? The answer is no? This paper provides some important insights to understand this more. (bookmark it) Paper summary: Adding procedural skills to an agent is usually

Big update: Among open-weight models, Kimi K3 (Max) is #1 in the Agent Arena with +9.75% net-improvement, surpassing GLM-5.2 (Max) at +7.12%, and landed the #1 spot across 5 signals (see below). Kimi

Happy to have @FireworksAI_HQ as our day0 launch partner and bring Kimi K3 to more developers. With Fireworks, you can now deploy and fine-tune the 2.8T Kimi K3 model with just a few clicks! Kimi K3 i

Kimi K3 is now available for inference & training in @FireworksAI_HQ. Crazy how easy they make it to tune frontier open models like K3 using LoRA adapters. Best time to figure out how to own your inte

Kimi K3 is now available on @digitalocean 's Serverless Inference! Developers can start building with our most capable model in minutes. .@Kimi_Moonshot K3 from Moonshot AI is now live on DigitalOcean

Kimi K3 is now available on Ollama’s cloud. To use it with Claude Code, run: ollama launch claude --model kimi-k3:cloud Currently Kimi K3 requires a Pro or Max subscription, and consumes extra usage c

love this frame. calls to mind the role of the hippocampus in human navigation (via place cells and grid cells), and how navigation is, in a sense, what makes agents *agents* vs plain old LLM calls in

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

The Opus 5 system card itself is a fun PDF to parse. It's 193 pages and stacked with labeled and unlabeled charts 📊 LlamaParse does a surprisingly good job on agentic (1.25c per page) and agentic plus

Kimi K3 is coming to Together AI on day zero, July 27. Start building with it the moment it launches, powered by Together AI inference for coding, agents, and production workloads. https://www.togethe

More than 300 million people turn to ChatGPT with health-related questions each week—and we’re continuing to improve how our models respond. We work with hundreds of physicians around the world to mea

// Programmatic Memory Enables Long-Horizon Reasoning // Keep the entire interaction log and search it. It works great and beats bespoke memory harnesses on long-horizon tasks. New research introduces

Progressive disclosure in agents doesn't scale. And its benefits seems agent harness dependent. (bookmark this one) Finally there is a proper study on using agent skills and the effect of progressive

Multiplayer mode with AI is incredibly underrated and underutilized. Cat Wu shared that 65% of Anthropic’s product engineering team PRs are closed via Claude Tag sitting inside of Slack, and not singl

It is clear open source models and harnesses are having a moment. There's a few factors at work 1/ It is now obvious that you can catch up to near-SOTA performance and do so with a clear training line

I’m very excited by this test time training work for robotic learning! It’s an awesome collaboration between @StanfordSVL and @NVIDIARobotics ! We scaled a robot model natively to 8,000 timesteps of c

Interesting surprise drop from Thinky! The Inkling model looks pretty solid on benchmarks, and it has some little surprises in its architecture: - Small conv layers in several places - An RMSNorm for

Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automations, writing lint rules to catch repeat

Bonsai 27B is a big step for local AI: 27B-class multimodal capability in a phone-class footprint. Congrats to @PrismML on the launch. Try Ternary Bonsai 27B on Together AI: https://www.together.ai/mo

Huge if true! We are talking about a 27B multimodal model that runs locally on a phone. That's wild! Bonsai 27B reaches up to 163 tok/s in 1-bit and 134 tok/s in Ternary on an NVIDIA GeForce RTX 5090.

🤗 MOSS-VL-Realtime is now open source on @huggingface . Built for real-time visual understanding over continuous video streams: 🧠 11B vision-language model 📜 Apache-2.0 license 💬 Ask questions at any

Today, we’re announcing Bonsai 27B: the first 27B-class model to run on a phone. Bonsai 27B is the new multimodal flagship of the Bonsai family. Based on Qwen3.6 27B, it brings a new capability tier t

one of the most memorable cooking pods we've had - both in terms of the content and the food! high protein percentage in both. In this episode, @EngramLab co-founder and CEO @dan_biderman joins @allen

BAMF is a term Elon Musk referenced on X (formerly Twitter), likely relating to a project, concept, or feature associated with his work at Tesla, SpaceX, or another venture. Without access to the spec

Key to this strategy is deterrence, 'Mutually Assured Compute Destruction' which gets its own section. It doesn't mention the generalization Mutually Assured AI Malfunction (MAIM) from Schmidt, Wang,

🚀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

New research from Meta. (bookmark it) It's on how to fix agents that forget previously made decisions. It's well know that long-horizon agents keep forgetting decisions they already made. Meta researc

arXiv:2408.02379v2 Announce Type: replace-cross Abstract: Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regul

Today, together with @kyutai_labs, we’re introducing our new Audio-to-MIDI model. It takes a finished recording, identifies the instruments playing, and returns separate MIDI tracks for each — voice,

ChatGPT Work reflects a shift in how people are using AI, moving beyond just answering questions to getting real work done across web, mobile, and desktop. You can ask ChatGPT Work to take on entire w

grok 4.5 made me give grok build a serious run today here's my honest first impression (non affiliated neutral view point): 1. grok build is a very good harness firstmate stretches harness capabilitie

Sam Altman discusses enterprise concerns about AI costs, highlighting that a 5.6 SOL rate represents significant progress in improving cost-efficiency metrics for AI task execution. The post reference

Great writeup from the University of Oxford. It's a taxonomy of LLM-based agent limitations. Good read for anyone shipping with agents. Benchmark scores keep climbing, yet the same agent failures resu

Massive open-source release! LingBot-Video isn't about video quality; it optimizes for physical reasoning, and it runs sparse: only 3B of 30B params are active at inference. MoE is finally showing up

Not another demo or benchmark. @ShoucongChen is a senior member of our technical staff. A real project, scoped at 1-month. Delivered in 4 days with GLM5.2 Fast. The best devs deserve >400 t/sec. Take