/Stream

All 1242 resources sorted by date, newest first

Article Sep 6, 2026

Understanding ChatGPT Work

What the subscription-only tier adds - code execution with internet access, a headless browser, persistent files and parallel sub-agents

ai
Article Aug 17, 2026

How the Astro team built a software factory to slash its issue count

Agent-driven triage took Astro from over 200 open issues down to 30.

ai oss
Article Aug 17, 2026

I put GitHub Copilot behind a MITM proxy

What Copilot actually sends home, from context assembly to interaction logging.

security ai
Article Aug 17, 2026

Now we have a timeline of the OpenAI accidental attack against Hugging Face

Full breakdown of how OpenAI agents probing infrastructure ended up hammering Hugging Face, with the internal timeline of what happened.

security ai
Article Aug 17, 2026

Revision prompting improves industrial LLM processes

Feed the model the original input, its original output and the input diff, then ask for a patch instead of a rewrite.

ai llm
Article Aug 17, 2026

Stolen thoughts

Encrypted reasoning traces replayed into jailbroken sibling models leaked keys, tokens and PII across 315,320 decoded blocks.

security ai
Tool Aug 17, 2026

Computer

Give your agent a computer.

ai agents
Tool Aug 17, 2026

Docker Sandboxes

Run coding agents in their own microVMs with a Docker daemon inside.

ai docker
Tool Aug 17, 2026

Foreman

A software factory that moves each GitHub or Linear task through classifier, analyst, implementer and reviewer stations.

ai agents
Tool Aug 17, 2026

OpenChamber

An agentic development environment that keeps code and session data local across multiple models.

ai tooling
Article Aug 3, 2026

Discovering cryptographic weaknesses with Claude

A model halved the effective key strength of the HAWK signature scheme and sped up an attack on reduced-round AES by up to 800x, working mostly on its own for a week

ai security cryptography
Article Aug 3, 2026

Domenic Denicola's agentic coding setup

Disposable VMs, Tailscale and worktrees — how a longtime JavaScript standards figure runs coding agents day to day

ai agents workflow
Article Aug 3, 2026

How Figma stays ahead of vulnerabilities with agents

Precision over recall was the whole game — 70% before agents were allowed to comment on PRs, and the shared policy became a de facto threat model

security ai agents
Article Aug 3, 2026

Kimi K3 architecture notes

LatentMoE, attention residuals, and dropping RoPE in favour of NoPE in a bigger open-weight model

ai ml architecture
Article Aug 3, 2026

MCP gets its largest update since launch

The protocol goes stateless, so remote servers run on serverless and edge infra or scale horizontally behind a load balancer

ai mcp protocols
Article Aug 3, 2026

The economic benefit of refactoring

Refactoring an AI-generated codebase cut token consumption for later updates by 83 percent and made navigation cheaper

engineering refactoring ai
Article Aug 3, 2026

The life of a Codex conversation on disk

Walkthrough of the journal file, caches and indexes behind a Codex chat — and why clearing a thread is not the same as deleting it

ai agents tools
Article Aug 3, 2026

The new rules of context engineering for Claude 5 generation models

Anthropic cut over 80% of Claude Code's system prompt for the newer models — smaller prompts, progressive disclosure through skills, and context assembled from skills, CLAUDE.md and memory instead

ai agents claude
Article Aug 3, 2026

Treat prompt changes like code deploys

Prompts are dependencies that shift production behaviour with no failing build, so gate them and default the gate to blocking

ai engineering
Tool Aug 3, 2026

Claude Code Merge Queue

Local merge queue for parallel coding agents, so simultaneous landings stop racing each other on push

ai agents tools