Search: “agents”

LLM agents loop, drift, and get stuck on hard reasoning tasks up to 30% of the time. Current fixes are either too blunt (hard step limits) or too expensive (LLM-as-judge adding 10-15% overhead per ste

`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

we are doing this podcast specifically to highlight the innermost details of building agents in production may be a little niche, but its a niche i like 🤷‍♂️ @hwchase17 Great content, really appreciat

what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool d

.@NVIDIA Nemotron 3.5 Super VL is now live on Together AI. An open-weight multimodal model built for visual reasoning and always-on agents that see, reason, and act across documents, screens, and vide

A spiralling legal crisis threatens to engulf OpenAI after its AI agents hacked dozens of companies and governments worldwide, with the prospect of a barrage of lawsuits marking the latest test of Sam

Agents write application code, but you still get paged at 2am when it breaks. We wanted to know whether AI could handle that part of the job too. Introducing Incident Arena: a benchmark that puts codi

And the incidents apparently continue. It is worth noting how much of this is agents trying to accomplish their goals during testing by reward hacking (which sometimes seems to include actual hacking)

Deepseek-V4.1-Flash is available now on Fireworks! It is a 552B Parameter MoE built for coding, cybersecurity, and agents. It is the ideal workhorse model that outperforms Opus 5 and GPT 5.6 Sol at 1/

The same people that are building the most advanced AI models and agents are those that are calling them alien, and state that they do not know how to reach alignment with AI. It might be possible tha

We congratulate Levent Alpöge and Tristan Buckmaster on their remarkable mathematical work. We (the researchers and the agents) did not see any of their work through any means until they released it p

How we think about the “wiki incident,” where our agents wrote to several internet sites: it’s past time for us to define standards for when and how we share misalignment incidents, not just misalignm

Over 4 petabytes of models and datasets have been uploaded to HF just last week by AI builders and their agents! That's the equivalent of ~800,000 HD movies. More than ever the storage and collaborati

Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advance

Breaking news: OpenAI admitted its internal monitoring system was not triggered until more than a week after its AI agents broke free of controls, accessed the internet and hacked start-up Hugging Fac

Confirming what we already knew: The OpenAI Hugging Face incident would have been prevented had OpenAI been monitoring the agents in any meaningful way. This wasn't a hard technical problem. It was an

IBM Granite 4.2 is now available on Ollama. 3B, 8B, 30B parameter open models made for enterprise agents. This model is free to use and is licensed for both research and commercial usage. The data cur

‘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

Banger paper on harness continual learning. (bookmark it) If you already are allowing your agents to rewrite their own prompts, skills, or memory files, this one is worth your time. (bookmark it) Cont

NVIDIA’s Nemotron 3.5 Lightning—a fast open AI model designed for always‑on agents that perform high‑volume, specialized work—has been launched on the Together AI platform as of 11 August 2026. NVIDIA

Neat example here of the agents communicating purely through file names, including adding base64-encoded attachments and using 'zz' prefixes to ensure their new message sorts to the bottom of the list

Routing for long-horizon coding agents is a big deal. @notdiamond_ai just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before ea

Really interesting concept -- instead of optimizing against static benchmarks or internally generated reward models, agents are evaluated through real economic interactions. Using an external market a

Are structured outputs in agents always good? This paper suggests that you might have to take a closer look. Your product's structured output surface is measurably more homogeneous than the chat surfa

New work led by @FlemmingKondrup and @tomjiralerspong highlights an important vulnerability in chain-of-thought monitoring for agents, I highly recommend giving it a read. Link to the paper: https://a

love to see two port cos collaborating😁 get private market data for your agents from @akta_pro with your @monid_ai account! We just killed PitchBook. Introducing Claude for private market data. Your a

Hugging Face Gemma Challenge results are in! 📈 Over 6 days, more than 100 AI agents and humans collaborated to make Gemma 4 inference 5x faster on a single NVIDIA A10G GPU. - Fastest result: 491.8 TPS

This post highlights a practical AI agent that operates intuitively without requiring explanation of its underlying mechanics, suggesting it has achieved a user-friendly interface or autonomous functi

Cursor has streamlined its project and repository selection interface to improve user efficiency, allowing developers to launch AI agents with fewer clicks. The update combines simplified navigation w

Vercel has acquired the Better Auth team to accelerate development of open source authentication solutions for applications and AI agents. This acquisition aims to strengthen Vercel's authentication c

Finally, Grok’s Speech-to-Text is now live in Grok Build You can now just dictate prompts directly to your coding agents using /voice or Ctrl + Space, powered by Grok Voice Just talk naturally for lik

Pinecone has released Nexus, a new product in public preview designed to enable AI agents to access and leverage business knowledge more effectively. Nexus appears to be a solution that integrates wit

Ethan Mollick predicts that multi-agent organizational structures will deliver better cost-to-performance ratios compared to simple task-based routing systems for AI applications. This suggests that m

There are basically two skillsets that matter more in the age of coding agents. The first is the one everyone talks about: product sense and taste. Code is cheap now, so knowing exactly what to build

Nous Research has released a feature or tool that allows users to display their AI agents in small, compact window sizes, improving UI flexibility and workspace management. This update addresses user

Introducing NVIDIA Nemotron 3 Ultra. A frontier smart open model built for long-running agents that need to plan, reason, use tools and keep working across complex coding, research and enterprise work

Data agents don't fail at writing SQL. They fail at knowing your business. Schemas show you the columns, but they don't tell you which view is canonical for ARR, how often each metric updates, or whic

Verification is the hidden bottleneck for knowledge work agents, especially in legal AI — complex, long-horizon work is graded by rubrics with dozens of strict criteria. In new research with @LangChai

just a small zoom out on the vibe shift: in Feb 2025 @soumithchintala was talking about his dream of personal, local, private agents, most people didn't believe him. it's June 2026 and @pewdiepie has

// The Efficiency Frontier // Cool paper on context management. As agents reuse the same documents and histories across many turns, the cheapest context strategy is not fixed. This work describes a pr

Cursor has introduced an auto-review mode feature that enables AI agents to execute tool calls with reduced approval requirements while maintaining safer execution practices. This feature streamlines

Having Grok Build sub-agents to iterate several ideas for me on data loading, batching, inference, and writing results to files for dense datasets before I went to sleep. It gave me a nice summary of

Banger paper from Harvard. AutoScientists drops the central planner entirely. Agents interpret shared experimental data, self-organize around promising directions, evaluate proposals before resource a

🚨 This is EXACTLY WHY ICE agents are FORCED to wear masks ICE Newark rioter: “I HAVE YOUR FACE, MOTHERF***ER” “Your WHOLE F***ING FAMILY is DEAD!” “Your KIDS. Your WIFE. ALL DEAD!” This is the type of

Boston Tech Week featured a session hosted by Mason Dry and Sydney Runkle with the Blitzy AI team focused on building deep agents. The event was promoted via Luma Events and appears to be an education

Gary Marcus shares a video clip discussing the intersection of AI agents and questions of responsibility, featuring contributors Thierry Souttiaux and Silicon Valley commentators. The post highlights