Knowledge catalogue
Great example of why you should 1. Run your agent on a separate machine from the sandbox it uses (e.g. sandbox as a tool) 2. Never set env vars in your sandbox. Instead, use something like LangSmith’s
I don't understand the path forward for Mythos releases. Google & OpenAI will have equivalent models, and they are approaching AI cyber risk guardrails differently, so they will presumably just releas
if your reaction to this is “haha openclaw bad, see prompt injection is the #1 danger” you: 1) havent sufficiently appreciated the layers to this tweet 2) havent seen enough ai api keys @gilpinskyy @d
Really curious when Gemini is going to join the Cowork & Codex race to build a local app that isn’t just for developers. Antigravity hasn’t posted updates to X in a month, and remains very software fo
Bloomberg: Sources: Mistral has been developing a cybersecurity-focused AI model and held discussions about it with European banks, which don't have access to Mythos — French artificial intelligence s
arXiv:2605.11496v1 Announce Type: cross Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and
The most expensive mistake in enterprise AI right now: treating FDEs as your whole transformation plan. Forward deployed engineers (FDEs) are important for custom deployments, but they won’t fix the c
A startup wants to pull magnesium from seawater without torching the environment. Another wants to take small language models to the podium for enterprise customers. Today @jason and @alex sat down wi
arXiv:2605.09611v1 Announce Type: new Abstract: This preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines. We measure conte
arXiv:2605.10052v1 Announce Type: cross Abstract: As artificial intelligence engineering paradigms shift from single-agent Prompt and Context Engineering toward multi-agent extbf{Coordination Engineer
Voice artificial intelligence startup Vapi Inc. said today it has raised 50 million in new funding to change the way people talk to computers, experience phone calls and interact with customer support
3 weeks since ml-intern launched and we just hit 1M messages exchanged. that's 3.3 agent-years of ML research in 21 days. 2 months worth of research every day. 17,383 training jobs total. talk about A
Georgia Wells / Wall Street Journal: AppMagic: Grok downloads fell to ~8.3M in April, from a high of 20M+ in January; Recon Analytics says Grok paid adoption in the US remains nearly flat YoY in Q2 —
At Google Cloud Next ’26 we announced Cloud Storage Rapid, a family of object storage capabilities for data-intensive workloads like AI and analytics. Out of the gate, Cloud Storage Rapid consists of
Compute is scarce and has to be bought years in advance, before companies know whether revenue will ever catch up. That is exactly the nature of the largest gamble in history. Heaven help the global e
Daniel Stenberg / daniel.haxx.se: curl founder Daniel Stenberg says Mythos identified five vulnerabilities in curl, but a manual review found three were false positives and one was “just a bug” — yes,
arXiv:2605.06673v1 Announce Type: cross Abstract: Aggregate metacognitive quality scores mask within-model variation across MMLU benchmark domains. We administered 1,500 MMLU items (250 per domain, un
arXiv:2605.06738v1 Announce Type: cross Abstract: Autonomous AI agents now transact at production scale -- 69,000 bots executing 165 million transactions across 50 million USDC in cumulative volume on
Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations
okay so from what i can tell, this is probably more about limiting secondary activity to control secondary price, than punishing existing SPVs secondaries can be a great price discovery mechanism for
arXiv:2605.07172v1 Announce Type: new Abstract: Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on loc
Maybe one of the only moats in 2026 is the context layer. AI improvements mean: ✅ UI/UX might simplify and consolidate. Instead of a lot of fancy buttons/knobs, you need simple, clean interfaces where
Boris Cherny attended a Claude developer conference and documented his experience in a short vlog, collecting conference merchandise and memorabilia including a tamagotchi toy and a pixelated 8-bit ve
Take Mythos seriously, but don’t panic. Here are the facts: • Mythos is a real threat. And it can really help with finding bugs (as @mozilla’s new report documents well). • It’s not unique; similar vu
We are less safe as a society by keeping Mythos (or any other smart model) tightly gated so only a few companies get it. Protecting 100 companies is not enough. There are 96 million open source projec
Legendary venture capital firm Andreessen Horowitz is backing the artificial intelligence-native “product team-as-a-service” startup Pit in its first major funding round. It served as the lead investo
Behind the Scenes Hardening Firefox with Claude Mythos Preview Fascinating, in-depth details on how Mozilla used their access to the Claude Mythos preview to locate and then fix hundreds of vulnerabil
arXiv:2605.03952v1 Announce Type: cross Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The chal
I repeat, the bubble is in the 'e' not the 'p' in today's PE ratios. The hucksters and talking heads will, as always, fail to realize until it's too late. But it's a very simple set up. Hyperscalers g
Simon Willison provided live coverage of the Claude with Code event keynote in San Francisco on May 6, 2026, via his blog. The post documents real-time updates and commentary from the keynote presenta
It feels like agent harness evolution runs on two axes that usually get conflated. There’s the temporal axis: simplify as models improve, stripping components that compensated for limitations the new
arXiv:2605.02964v1 Announce Type: new Abstract: Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomou
I recently talked with Joseph Ruscio about AI coding tools for Heavybit's High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my highlights, including my
Come and join us, we're hiring across almost all roles 🚀https://www.langchain.com/careers Companies I'd consider going to if I ever had the urge to try something new. 1 Thinking Machines Lab 2 OpenAI
Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next '26, we introduced Gemini Enterprise Agent Platform to he
For those affected, you're going to see a lot of advice on social media for what to do next. I like Claire's tweet a lot. Here's my version of her tweet for millennial/gen x business professionals: -
Alice Speri / The Guardian: Letter: UK-based Google DeepMind workers voted to unionize with the Communication Workers Union and Unite in April, representing 1K+ staff, amid the US DOD deal — Exclusive
Parllama is a TUI (Text UI) application designed for easy management and use of Ollama-based LLMs that also works with major cloud-provided LLMs. It provides core model management features including f
arXiv:2605.02801v1 Announce Type: new Abstract: As large language model (LLM) agents evolve from isolated tool users into coordinated teams, reinforcement learning (RL) must optimize not only individu
See you all soon! We've got some fun announcements ahead. I'll also be doing a workshop on 'how we Claude Code' with some workflows I'm excited to share. Don't worry if you're not there, everything wi
arXiv:2605.02398v1 Announce Type: cross Abstract: As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not kn
SemiAnalysis, a semiconductor industry analysis publication, has a readership that is approximately 90% male according to founder Dylan Patel. This gender skew toward male readers is notably higher th
Meir Orbach / CTech: Cisco agrees to acquire Astrix Security, which helps companies monitor and control the permissions granted to AI agents, a source says for approximately $400M — The Israeli startu
arXiv:2605.00133v1 Announce Type: new Abstract: Modern crop advisory systems exhibit a critical limitation termed extit{economic blindness}. These systems primarily optimize for biological yield, ofte
This is probably better messaging than just “own your harness.” Yes, open models will need custom harnesses, but that is a means to an end. The end is utilizing models without being handcuffed to Anth
All the Doomers and hawks are lining up behind this distillation 'attack' farce because they want to see open source banned. It's really as simple as that. They want to take away your right to choose,
arXiv:2604.27006v1 Announce Type: cross Abstract: Context: Study screening in systematic literature reviews is costly, inconsistency-prone, and risk-asymmetric, since false negatives can compromise va
I have been testing DeepSeek-V4-Pro with the Pi coding agent. I am mindblown by how well it works out of the box. A few notes: I spent a few hours building an LLM wiki with an agent powered entirely b
Wall Street Journal: Sources: Coatue formed Next Frontier in 2025 to buy land for data centers; Next Frontier has a JV with neocloud Fluidstack that has raised $5.7B via junk bonds — Philippe Laffont'
Claude Code is tuned for Claude. Codex is tuned for OpenAI models. Until now, 𝚍𝚎𝚎𝚙𝚊𝚐𝚎𝚗𝚝𝚜 had fixed harness defaults, which meant it couldn't take advantage of the provider-specific optimizations that
Our evaluation of OpenAI's GPT-5.5 cyber capabilities The UK's AI Security Institute previously evaluated Claude Mythos: now they've evaluated GPT-5.5 for finding security vulnerability and found it t
arXiv:2604.24966v1 Announce Type: cross Abstract: Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a p
arXiv:2509.11295v2 Announce Type: replace Abstract: Developing effective prompts demands significant cognitive investment to generate reliable, high-quality responses from Large Language Models (LLMs)
If you want to know whether the AI bubble is bursting, there's only one publicly traded company that will tell you: Oracle. That's right, the database company. Oracle has burned its boats and pivoted
New in Deep Agents: Harness Profiles. https://www.langchain.com/blog/tuning-deep-agents-different-models ✅ Model-specific profiles to adjust prompts, tools, and middleware. 📦 Profiles for @OpenAI, @An
Xiaomi MiMo-V2.5-Pro achieves multiple breakthroughs in the latest Arena rankings (Apr 26, 2026) 🔥 🏆 Text Arena (Expert) — #6 globally | #1 open-source model Also #1 among Chinese models, with Xiaomi
arXiv:2505.14549v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions oft
arXiv:2604.23341v1 Announce Type: cross Abstract: The deployment of Large Language Models (LLMs) as assistants in electric grid operations promises to streamline compliance and decision-making but exp
arXiv:2604.23347v1 Announce Type: new Abstract: We present a comprehensive evaluation of Large Language Models (LLMs) on Computer Science (CS) Data Structure examination questions. Our work introduces
I pulled 3,182 tweets analyzing @NousResearch Hermes Agent versus Claude Code to understand exactly why developers are choosing one or the other I want to figure out why people use Hermes vs Claude/ C