Knowledge catalogue
This article discusses the integration of Benchmaxxer Repellant into the Open ASR (Automatic Speech Recognition) Leaderboard, likely a tool or mechanism designed to prevent gaming or manipulation of l
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
Managing agents and their actions can quickly grow in complexity and introduce security risks unique to AI. To address these challenges, at Google Cloud Next we announced Agent Gateway to provide simp
LLM 0.32a0 is an alpha release of Simon Willison's LLM Python library and CLI tool for accessing large language models, featuring consequential architectural changes. The release includes two key chan
LlamaIndex have a most excellent open source project called LiteParse, which provides a Node.js CLI tool for extracting text from PDFs. I got a version of LiteParse working entirely in the browser, us
This post documents a method for extracting the text prompt used by an image generation AI by examining network traffic in a web browser's developer tools. Simon Willison demonstrates that prompts can
arXiv:2604.18292v1 Announce Type: cross Abstract: Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model
The Supabase blog post covers how Supabase developed and open-sourced the Stripe Sync Engine — an open-source tool that uses Stripe webhooks to keep a Postgres database of billing data in sync with St
Armin Ronacher (mitsuhiko) shared slides from a talk he presented at the AI Engineer conference, likely covering topics related to AI engineering, developer tools, or software development practices gi
Tool: SQLite Query Result Formatter Demo See my notes on SQLite 3.53.0. This playground provides a UI for trying out the various rendering options for SQL result tables from the new Query Result Forma
Vercel's open-source Knowledge Agent Template enables developers to build AI knowledge agents using a filesystem and bash tools (grep, find, cat) instead of the traditional vector database, embeddi...
The Chat SDK is a unified TypeScript library designed for building chat bots. This tool allows developers to maintain a single codebase to create chatbots that reliably function across multiple pla...
Vercel's AI builder v0 has acquired the team behind new.website, a tool founded to make creating beautiful, production-ready websites effortless through built-in primitives like forms, databases, S...
I'm not able to fetch URLs or browse the internet directly. However, I do have access to a web search tool — let me try searching for this content instead. The specific tweet (status ID 20421847775...
Highlights: 👉 28% coding improvement over GLM-5 with refined RL post-training 👉 Better long-horizon execution across hundreds of rounds and thousands of tool calls 👉 Thinking mode, tool calling, and s
I know everyone's excited about 3.8, but honestly I'm still refining 3.6. And I hate the way 3.8 talks, so... I keep seeing all these posts about what's the use of open source, so I figured I'd submit
In production systems today, most AI agents operate as lightweight dispatchers. They parse a prompt, make an API call, retrieve a record, and hand back control. Their execution is fast, stateless and
arXiv:2610.22244v1 Announce Type: cross Abstract: Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users writ
NVIDIA Nemotron 3.5 Super NVIDIA Nemotron 3.5 Super is a vision-language model for coding, reasoning, tool use, and document understanding. It pairs a 120B-parameter hybrid Mamba-2/Transformer mixture
arXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine
arXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effec
arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply
I've been optimizing long-running agents: rewriting their prompts, tools, skills and subagents, and keeping the changes that score better. I've been working on some version of this problem for over a
Release: ttok 0.4 ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library. It hasn't been in updated in a couple of years, but I finally fixed a Click warning, updated CI,
arXiv:2610.07257v1 Announce Type: new Abstract: Developers increasingly run a fleet of coding agents side by side on one workstation. The tools they reach for, terminal multiplexers like tmux and a ne
Developers aren’t becoming more careless; they’re being outpaced. The tools that let developers create more software should also take on more of the work of protecting it. The post Secret protection m
arXiv:2610.08170v1 Announce Type: cross Abstract: Agentic VLM pipelines increasingly pass the same static visual evidence through multiple specialist agents and tools. This design creates an orchestra
arXiv:2610.05281v2 Announce Type: replace Abstract: Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data
Over the past several months, we conducted an empirical post-mortem investigation into 109 autonomous AI agent security incidents (cataloged with 193 falsification criteria across tool-use and multi-a
arXiv:2601.07148v4 Announce Type: replace-cross Abstract: Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchm
arXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python va
arXiv:2609.38923v1 Announce Type: new Abstract: Working agents need to read diverse files, coordinate tools, and produce deliverables. Training such agents requires tasks built on many real files with
arXiv:2609.27342v1 Announce Type: new Abstract: Cutting changes both the shape and topology of deformable objects, making accurate simulation challenging for robotic manipulation. A simulator must tra
arXiv:2609.27067v1 Announce Type: cross Abstract: Large language model (LLM)-based agents use Electronic Design Automation (EDA) tools to generate and revise register-transfer-level (RTL) designs unde
arXiv:2609.26445v1 Announce Type: cross Abstract: This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like ca
arXiv:2609.24446v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subseque
arXiv:2609.23925v1 Announce Type: cross Abstract: We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, a
arXiv:2609.21306v1 Announce Type: new Abstract: A common requirement across organizations is to have a tool that can identify file types based on their contents, particularly in the cybersecurity doma
Okay, this one seems probably really odd (or maybe not), but most harnesses operate within token spaces. That is, every tool output, even batching of tool outputs, go back up into inference calls. Lea
arXiv:2609.17686v1 Announce Type: cross Abstract: Three recent results describe what look like unrelated LLM reliability problems. Yin et al. (2026) show reasoning RL collapses tool-reliability repres
Meta has launched its new Muse assistant, marking the company's first real foray into AI-powered productivity tools. The company says its AI agent can 'take the busywork off your plate' by helping you
**Title:** llm 0.35 **Summary:** Version 0.35 of the `llm` tool offers a command‑line interface for interacting with large language models. It allows users to issue prompts and retrieve model response
Tool: Mercator ↔ Equal Earth I got curious about the Equal Earth map projection that was recently voted on at the UN so I had GPT-6 Astra (medium) in ChatGPT Work build me this animated transition bet
arXiv:2609.01693v1 Announce Type: cross Abstract: Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one a
arXiv:2609.00384v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and i
Introduction Beginning in 2024 Mandiant investigated a string of compromises affecting Brazilian financial services, retail, and eCommerce organizations. Google Threat Intelligence Group (GTIG) tracks
Tool: GeoJSON Map Viewer I was helping Natalie gather some maps of local political boundaries (for the Granada Community Services District and the Midcoast Community Council and found a need to displa
arXiv:2608.30672v1 Announce Type: new Abstract: Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic syste
arXiv:2608.29357v1 Announce Type: new Abstract: Multimodal search agents answer visual questions by interleaving image understanding, web retrieval, tool use, and evidence synthesis. Strong systems ex
arXiv:2608.31057v1 Announce Type: new Abstract: Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles an
Pure scaling of LLMs did actually hit a wall; neurosymbolic AI rescued it. AI didn’t hit a plateau; pure LLMs did — until people used harnesses and tools to complement their weaknesses. Which was alwa
arXiv:2608.27492v1 Announce Type: cross Abstract: Publicly-acceesible face-manipulation tools have made deepfake creation accessible to non-expert users. Against these, existing defenses are mostly po
arXiv:2608.28439v1 Announce Type: new Abstract: One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a struct
arXiv:2608.26991v1 Announce Type: new Abstract: Powerful code agents can execute scripts, call tools, and manage files, yet many important applications remain accessible primarily through graphical us
arXiv:2608.27184v1 Announce Type: cross Abstract: Electronic design automation (EDA) has advanced engineering productivity through successive generations of tooling that progressively automate synthes
arXiv:2608.24524v1 Announce Type: cross Abstract: Feature attribution is a central tool of model interpretability, yet the software through which it is applied remains fragmented: individual tools spe
Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that drive shipped tool-ca
arXiv:2608.24358v1 Announce Type: new Abstract: Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-qu
For two years, the field has gotten very good at training models, and it still hand-wires the agents around them. Whether an agent plans, searches, calls a tool, or checks its own work before answerin
arXiv:2608.21027v1 Announce Type: new Abstract: LLM agents are emerging as an important paradigm for real-world tasks that require reasoning, tool use, and sequential decision-making. As these agents