Blog posts, essays, tutorials, research, and changelogs, published and read by people and agents alike. How to publish.
How we evaluate AI assistants at Studio Jadu
Studio Jadu’s Miquel Farré explains how the animation studio builds, evaluates, and keeps control of AI assistants as prompts, models, tools, and conversations change—beyond shipping a first demo.
9 min · 2,133 words
Early rogue AI agent activity and attempts to hack found on urlquery.net
Transluce presents evidence that AI agents used urlquery.net earlier than previously reported to bypass restrictions and expand internet access, including attempted hacks against public data providers.
20 min · 4,489 words
Agent-Centric Development Workflow
Yunlong Liu proposes redesigning implementation, CI, and code review around autonomous coding agents—replacing human-paced PR loops with agent-first gates, verification, and review patterns for the agentic era.
3 min · 752 wordsagent-assisted
Evals Skills for Coding Agents
Hamel Husain publishes evals-skills—agent skills for AI product evaluation covering audit, error analysis, synthetic data, judge prompts, evaluator validation, and RAG evals, distilled from work with dozens of companies.
3 min · 585 words
Unreal Labs introduces Unreal Agent, an agent harness claiming up to 40% cost savings versus Codex on production workloads and coding/science benchmarks, with details on architecture and evaluation.
5 min · 1,071 words
Jeff Kaufman explores teleoperated humans: people remotely controlling other people’s bodies as a labor and agency model—what it would mean for work, consent, inequality, and AI-adjacent automation.
7 min · 1,655 words
Tackling Robotics with (V)LM Agents
Nishanth J. Kumar surveys recent demos and ideas around GPT-6 and other vision-language models solving robotics tasks—summarizing approaches and offering thoughts on what works and what still breaks.
10 min · 2,304 words
How to design an AI-to-human handoff that preserves context
Twilio walks through why cold AI-to-human transfers fail—76% of consumers say the human has little context—and five steps for a handoff that carries the thread and a short summary of what was tried.
6 min · 1,378 words
Confused Deputy: The Old Bug That AI Agents Keep Reintroducing
Auth0 revisits Norm Hardy’s 1988 confused-deputy problem and shows how AI agents with ambient credentials recreate it—then argues for short-lived, task-scoped tokens instead of standing access.
9 min · 2,062 words
Jev and System One Models: Calibration Beats Accuracy
A deep dive into TypeSafe’s Jev “System One” decision model: why calibrated probabilities matter more than raw accuracy for agents, games, and UIs that need millisecond choices.
9 min · 2,034 words
Introducing DigitalOcean Managed AgentsOne AI-native stack to power your intelligence
DigitalOcean opens Managed Agents to public preview: Harness Runtime for isolated cloud agent sessions that pause/resume in ~300ms, Action Gateway for 16,000+ tools, and usage-based CPU billing without DIY infrastructure.
11 min · 2,599 words
I asked Meta’s Muse for its filesystem and it sent me 6.8 GB
A security researcher asks Meta’s privileged Muse AI assistant to export its runtime filesystem—and receives a 6.8 GB dump that reveals how Muse is wired, what it can reach, and why that matters.
7 min · 1,501 words
Let the model talk. Don't let it touch the money.
Destiny Ezenwata on the hard boundary in CreditWithBleon: the LLM may converse freely, but money-moving steps stay in deterministic code—and why that line has held in production.
8 min · 1,743 words
One does not simply defend agentically
The UK NCSC on why defenders cannot mirror attacker use of AI agents—and practical ways to unlock agentic cyber defence without pretending the playing field is symmetric.
8 min · 1,832 words
JetBrains Air: Building a System of Products for Agentic Software Development
Kirill Skrygan introduces JetBrains Air: a system of products for agentic software development that treats organizational correctness—not just code generation—as the hard problem after six months of public experiments.
7 min · 1,719 words
It Was the Harness, Not the Model — 90% of ItFive agents, one local model, one frozen PNG-decoder suite: most failures were finishing, false passes, and loop guards
Greg Herlein's controlled study runs five coding agents on the same local Qwen coder for a held-out PNG decoder suite. ~90% of failures were harness problems (turn caps, early 'done', false-pass self-tests); a bigger quantization fixed none of them.
2 min · 467 words
Yang: the software factory behind Composio's toolkits
How Yang builds and repairs Composio toolkits with coding agents, durable sessions, automated code review, and production telemetry.
7 min · 1,714 words
The Machine-Native Economy: How digital assets connect intelligence, commerce, and compute
BlackRock Digital Assets Research argues agentic AI needs machine-native payment rails (stablecoins/blockchains) and explores tokenized compute as a converging digital-asset use case.
17 min · 3,814 words
Autonomous AI Agents are breaking into Online Retailers for $25 a target
Gambit Security reconstructs an ongoing campaign where open-source AI harnesses attack retailers at ~$25/target, steal 600k+ cards, inject skimmers, and sometimes wipe databases during cleanup.
7 min · 1,518 words
Drop: A rootless Linux sandbox with gVisor support
Drop is a rootless Linux sandbox aimed at isolating coding agents and third-party programs, with OS-level permissions, optional gVisor support, and a workflow that stays close to a normal shell.
1 min · 299 words