Knowledge catalogue
arXiv:2607.01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testin
Something about this year’s @aiDotEngineer World’s Fair just hit different. Last year was the year of “let the agents rip.” This year was the year of realizing that autonomy without structure creates
my fave question, talked about this coding agent Eval+Improvement loop infra + UX in my AIE talk yesterday! biased but LangSmith is the best spot to Eval + continuously improve your coding agents, and
Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (t
arXiv:2606.31551v1 Announce Type: new Abstract: Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents become increasingly capable at software
'For agents within an actual product, I have gravitated to using LangChain DeepAgents. I feel like their base harness is less heavy, and their abstraction for building agents that use skills and tools
Frontier open models with enterprise governance means rebuilding workflows from scratch. Move faster with Fireworks on Foundry. GLM 5.2 is live on Microsoft Foundry. With FireConnect enabled, devs can
arXiv:2606.32025v1 Announce Type: new Abstract: Recent LLM agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for perfor
good post on the value of knowing whats going on in your harness 'For agents within an actual product, I have gravitated to using LangChain DeepAgents' The frontier model lab harnesses are amazing - d
Great paper on managing agent skills. Skill libraries keep growing, and picking the right skills has become a bottleneck for coding agents. The defaults are to expose the agent to the whole skill coll
Every article saying 'THIS IS THE NEW JOB OF THE AI ERA' is one of two jobs. And the first is a lie imo. The first job, is usually something that an AI lab is hiring for and the news blows it complete
arXiv:2606.30560v1 Announce Type: cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge r
Tool: HTML table extractor Yet another in my growing collection of paste-conversion tools. This one accepts pasted rich text from browsers (with embedded HTML tables) and converts every detected table
I put together a new article on setting up local coding agents with open-weight models. Everything runs 100% locally. I thought it might be useful putting this together because many people asked me ab
arXiv:2606.26216v1 Announce Type: cross Abstract: We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability det
Taps sign We believe in broad access and plan to make GPT-5.6 Sol, Terra, and Luna generally available in the coming weeks. For now, at the request of the U.S. government, we’re starting with a limite
team cooked, spicily We’ve designed and built our first AI chip: Jalapeño. Designed from the ground up by OpenAI and brought to production with @Broadcom, Jalapeño is purpose-built for the LLM workloa
This is a fascinating and important set of data which shows us where things are going, using OpenAI as a canary in the coal mine. The chatbot era is over, and agentic systems are coming to tasks beyon
arXiv:2606.24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However,
simonw/browser-compat-db Inspired by Mozilla's new MDN MCP service - source code here - I decided to try converting their comprehensive mdn/browser-compat-data repository full of browser compatibility
We’ve designed and built our first AI chip: Jalapeño. Designed from the ground up by OpenAI and brought to production with @Broadcom, Jalapeño is purpose-built for the LLM workloads powering ChatGPT,
Gray Swan: Red-Teaming after Mythos & the coming AI security crisis https://www.latent.space/p/gray-swan @GraySwanAI cofounders @zicokolter and Matt Fredrikson explain why AI security is fundamentally
How does it work? Sakana Fugu is itself an LLM, trained to call various LLMs in an agent pool, including instances of itself recursively. Fugu dynamically orchestrates the world's best models to tackl
New listen: @GraySwanAI cofounders @zicokolter and Matt Fredrikson sat down with @swyx on @latentspacepod to unpack why AI security is its own discipline; not just 'cybersecurity with AI.' As agents l
Patch the Planet is our effort to help open source maintainers move from security findings to merged fixes. We’re working with Trail of Bits, HackerOne, Calif, researchers, and maintainers to bring Co
This morning on Hacker News I saw Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance, describing a small but effective inpainting model - a model where you can mark region
We want to help all companies be secure, working with the USG and the security ecosystem. *The full version of GPT-5.5-Cyber is here; state of the art performance on CyberGym. *Patch The Planet and Co
Temporary Cloudflare Accounts for AI agents The announcement says this is 'for AI agents' but (as is pretty common these days) the AI hook isn't really necessary, this is an interesting feature for ev
'Verifiable results (True/False) combined with a solution space exploration technique' - very well put. Crux of neuro-symbolic #ai, what @GaryMarcus has been shouting about it for decades. Crux of the
CyberAgent reports about 2,000 internal Claude Code users and describes its governance, training and software-delivery operating model; no measured outcome is published.
arXiv:2606.11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the
arXiv:2606.09833v1 Announce Type: cross Abstract: AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration b
Usage share of OpenAI grew vs Anthropic yesterday despite Mythos 5 / Fable 5 launch Multiple power users at SemiAnalysis tried Mythos / Fable Got refusals for nonsensical reasons Got pissed off at Ant
arXiv:2606.09446v1 Announce Type: new Abstract: Advances in handwritten text recognition have enabled large-scale transcription of historical documents, but still provide limited access to interpretab
arXiv:2606.07943v1 Announce Type: cross Abstract: Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A pr
Amazon Bedrock AgentCore Runtime gives each agent session its own isolated microVM with a persistent workspace, secure tool access through Gateway, and built-in observability—so you can run Claude Cod
So excited to be opening up OpenEnv to the whole community. It will now be owned by @huggingface , Meta-PyTorch, @reflection_ai , @UnslothAI , @modal, @PrimeIntellect , @NVIDIAAI , @mercor_ai , and @f
arXiv:2606.05525v1 Announce Type: new Abstract: Recent advances in agentic visualization have enabled the translation of natural language into executable scientific visualization (SciVis) workflows. W
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratc
A couple of weeks ago we started rebuilding the 𝚑𝚏 CLI with AI agents in mind. it now detects when an agent is using it and gives clean, token-efficient output, next-command hints, and more, all desig
I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HT
At Google Cloud, our goal is to let you run large-scale analytical and data science workloads with maximum efficiency so you can process big data pipelines, machine learning, and ETL tasks. We recentl
arXiv:2606.02644v1 Announce Type: cross Abstract: Agentic scaffolds have dramatically improved LLM performance on complex, long-horizon tasks, yielding both broad benefits and amplified risks in domai
A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon
arXiv:2606.03056v1 Announce Type: new Abstract: As LLM agents adopt large skill libraries, selecting the right subset becomes a structural problem rather than a similarity-matching one: skills depend
arXiv:2606.03907v1 Announce Type: cross Abstract: Agentic AI coding tools write code with increasing autonomy and in doing so decide when to import a library and when to implement functionality from s
arXiv:2603.24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on whi
One of the new, buzzy jobs in Silicon Valley is the AI Forward Deployed Engineer (FDE), an engineer who is embedded within a client organization to help customize solutions, such as building and tunin
This pod was an incredible gift to the community: not only our first pod about @xAI, but Ethan really indulged on all our questions on how to train a SOTA Videogen world model, including specific area
I’ve been saying this from day 1. Despite their launch video getting 50M views, Cowork was @AnthropicAI biggest mistake. I've been loyal to Claude but it would be really nice to have these tabs be con
One annoyance is each tab is missing features that would be really nice to have in a combined interface - why doesn't Cowork have a `fork` feature on threads? - why doesn't Code have a concept of 'Pro
arXiv:2605.29801v1 Announce Type: new Abstract: Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhi
Had a blast yesterday attending at @techeurope_'s Applied AI Conference in Berlin! I had a talk about building document agents and agentic development in general, that you can find here: https://astra
arXiv:2605.29059v1 Announce Type: cross Abstract: Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studi
This is a diary entry to myself, so I remember what AI was like today. It's just going to be a bullet-list stream of consciousness. - There are still so many leaders that have never seen an agent run
arXiv:2605.28065v1 Announce Type: new Abstract: AI agents are increasingly useful for biological data analysis, but existing benchmarks mostly test broad biological knowledge, executable workflows, or
arXiv:2603.03194v2 Announce Type: replace Abstract: Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software en
For future-proof, build AI that's composable. Regardless of what you use, all these should be composable, iterative, and customizable: - LLMs - Evals - Automations - MCP/CLI tools - Skills/Memory/Cont
Krea is now built in to Hermes Agent as an image generation API provider, allowing your agent to use Krea 2: a new foundation model trained from scratch to balance aesthetic quality and fine control,
arXiv:2605.26548v1 Announce Type: cross Abstract: Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. E