Search: “context”

this one is doing v well btw if you want the popular vote filter on the firehose of all the things @patrickdebois was one of the track keynotes i gave a 'blank check' to based on his sincere support s

it's always funny to me when these bot posts say we *just* launched deepagents... like nah man we've been carving this stone for close to a year now! Long-running agents almost always fail because the

This appears to be a casual social media post by AI researcher Gary Marcus discussing competitive dynamics in the AI field, with a conversational reference to Mark Zuckerberg as a notable figure or 't

tweeted about this yesterday and Cursor already dropped the alpha today! 🚀very cool to see how us, them, and others have converged on good design patterns in Agent + Harness Engineering: 1. Tuning dif

🚀 Introducing FlashQLA: high-performance linear attention kernels built on TileLang. ⚡ 2–3× forward speedup. 2× backward speedup. 💻 Purpose-built for agentic AI on your personal devices. 💡Key insights

I used to think the best way to come up with ways to use AI was to think about a painpoint or a problem and see if AI can make it better. I no longer think that. Why? Because that put every person int

🆕 Today, we're releasing the public preview of Workflows, the orchestration layer for enterprise AI. 🌎 Enterprise teams have capable models. What they don't have is a way to run them reliably in produ

Continued weak spots of AI, from the point of view of a business professional and not a PhD biochemist: 1) SVGs. The ability to 'illustrate' and have that thing be infinitely scalable. See below image

Sebastian Raschka has updated his LLM architecture gallery with higher resolution figures and improved summaries, including coverage of the DeepSeek V4 model architecture. This resource provides visua

Inference that never sleeps, for agents that never stop. 'Why cowork when you can delegate?' That's @DhruvBatra_ on @yutori_ai's new Delegate — an always-on agent that monitors, researches, and acts a

A nice paper worth checking out. (bookmark it) For a long time, we have had machines that work astonishingly well before we had a real theory of why. This paper argues that the scattered pieces are be

DeepSeek V4 by @deepseek_ai just dropped! SGLang is ready on Day 0 with a full stack of optimizations from architectures to low-level kernels. We also deliver a verified RL training pipeline in Miles

Clem Delangue highlights a significant development in local inference technology, noting that a project (referred to as 'whale bros') has released their work as open source. The post emphasizes the im

LangSmith for Startups Spotlight: @AdaptiveBuilds Adaptive is the AI-native project accounting platform built for construction. They embed AI agents directly into job costing, billing, and forecasting

Probably the most useful advice I can give you if you run an ad agency, a marketing company, a production studio, or anything in that space. Hear me out. I’ve spent a decade talking to teams about thi

These pelicans are kind of angry looking! Left is deepseek-v4-flash, right is deepseek-v4-pro - both generated using OpenRouter via my LLM tool 🚀 DeepSeek-V4 Preview is officially live & open-sourced!

Ethan Mollick discusses the phenomenon of users entering deeply immersive, flow-like states while intensely interacting with advanced AI models, suggesting the need for better terminology to describe

🎙️ Talked to @ListenLabs co-founder + CTO @florian_jue in the latest Max Agency. Really enjoyed hearing about the architectural decisions behind their agents, their self-reviewing feedback subagents,

Worth a read if you are building production-grade AI agents. // Stateless Decision Memory for Enterprise AI Agents // Most of the interesting AI agent papers right now are about capability. This one i

OpenAI has released workspace agents in research preview for ChatGPT Business, Enterprise, Edu, and Teachers subscription plans. Workspace agents are AI assistants designed to work within organization

I built a web analytics system to track traffic and events across all my @Replit projects in one place. Drop-in @posthog stack: → Full analytics dashboard → Reverse proxy (beat ad blockers) → AI skill

A useful ward against slop story/science posts on X is noting which is in the character limit. All of the models struggle to do 280 character summaries on their first pass, and most of the people crea

Going from local to production with agents can be tricky, especially when you go from a single user (you, the developer) to multi-tenant systems. Great blog from Sydney on best practices for doing thi

memory will be the great lock in and everyone knows it, so are rushing to get there first memory should be open! Last week, we released a preview of memories in Codex. Today, we’re expanding the exper

🤯QWEN 3.6 35B-A3B IS INSANE AT CODING @unslothai recently dropped Qwen3.6-35B-A3B-GGUF The first open Qwen3.6 model and it’s solid. This MoE beast is cooking on benchmarks: 🧠SWE-bench Verified: 73.4 (

The second most important release of the LLM era (after GPT-3.5), featuring what was likely the most important chart. Still seems surprising to me that OpenAI told everyone about the biggest advance i

This is also consistent with what OpenAI said at the time! https://x.com/polynoamial/status/2046064264189026587?s=20 @emollick We felt it was the right thing to do. People deserved to know what was co

this is probably the best writeup we have on what makes agents production grade - there’s a lot of failure modes for agents we’ve learned over the years, most of which are articulated here Also it’s b

I am very proud of our team for releasing EDINET-Bench, and it is fantastic to see a Japanese financial dataset recognized at #ICLR2026 this week. We need more diverse, non-English datasets to evaluat

Need to secure your production agents? @Cisco AI Defense Runtime Protection can integrate into your LangChain agents through middleware and produce a consistent runtime contract. 📄 What you need to kn

Today, Clearwing has replicated Glasswing's discovery of the @FFmpeg vulnerability using Codex-5.4 as the backend. I am going to attempt the same today, using @Alibaba_Qwen 3.6 on @ollama running on m

`deepagents deploy` now supports user scoped memory! add a user/ directory in your project so each user gets their own writable AGENTS.md, seeded on first deploy and persisted across conversations. yo

Emad Mostaque, founder of Stability AI, posted a tweet referencing Allbirds, likely drawing a comparison between the sustainable footwear brand's business model or marketing approach and something rel

New course: Spec-Driven Development with Coding Agents, built in partnership with @jetbrains, and taught by @paulweveritt. Vibe coding is fast, but often produces code that doesn't match what you aske

Big release here! Async subagents will become more and more of a thing, as subagents get longer running and you don’t want to block the event loop 🚀 deepagents 0.5 release 👉 Async subagents - kick off

Is there somewhere a collection of the best agent/coding harnesses for each models, especially open-source and local ones? In my opinion, the biggest reason why people are struggling with open/local m

Love seeing this open-sourced. Had a great chat with @nicoalbanese10 some weeks ago where he hinted to something like this. Great reference architecture for cloud coding agents. Open Agents gives you

one-shot podcast from news with @flymy_ai's new agent builder (just tested it), it: - researched news - created a transcript - created a voice for each part - stitched it together full prompt + output

Memory operations, including retrieval, prioritization, compaction awareness, should be native and baked into the harness. 𝐖𝐢𝐭𝐡𝐨𝐮𝐭 𝐭𝐡𝐞 𝐩𝐫𝐨𝐩𝐞𝐫 𝐢𝐧𝐭𝐞𝐫𝐚𝐜𝐭𝐢𝐨𝐧 𝐛𝐞𝐭𝐰𝐞𝐞𝐧 𝐡𝐚𝐫𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐦𝐞𝐦𝐨𝐫𝐲, 𝐦𝐞𝐦𝐨𝐫𝐲 𝐚𝐥𝐨𝐧𝐞 𝐢𝐬 𝐩𝐨

The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so

if you don't own your harness, you don't own your memory this is so true. even though Codex is an open source, it generates an encrypted compaction summary (that is not usable outside of the OpenAI ec

MiniMax-M1 is a large-scale open-weight reasoning model developed by MiniMax, featuring a hybrid Mixture-of-Experts (MoE) architecture with 456 billion total parameters (activating 45.9 billion per to

This one gives a lot of perspective over the fact that memory isn't just a plugin anymore. My take is, each approach has it's tradeoffs but for me the mental model is, if the memory is more than or 80

Memory + harness, or as @matt_slotnick put it, memory + intent. Something I describe a lot about @usebrief, that *why* you remember something is more important than pure recall. A moment that’s trivia

Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that only grows as agents get better at learning a big part of agent

What if owning the memory layer goes far beyond escaping lock-in? What if memory becomes fully editable intelligence? You could debug bad patterns, reinforce good ones, and crucially synthesize new on