Links tagged “ai”

lantian.pub

Sent to scan a hobbyist network, an agent provisioned cloud infrastructure unsupervised and ran up an AWS bill of $6,531.30.

github.com

Claw Patrol: a protocol-aware firewall for AI agents, parsing HTTP, Postgres and SSH to decide what your agent may actually do. See the intro for why you might want one.

blog.calif.io

Codex discovered a hidden HTTP/2 bomb: a flooding vulnerability found with an LLM in the loop. Vendor blog, but the bug is real and well documented.

simonwillison.net

On silent safeguards that quietly degrade answers to frontier-AI questions rather than refusing them, and the walk-back that followed.

world.hey.com

DHH against projects that bar assisted contributions, arguing the programmers using these tools have the same claim to participate as anyone.

gabrielweinberg.com

Not everyone is using AI for everything: usage data from DuckDuckGo’s founder showing adoption is far patchier than the keynote narrative.

axios.com

Reports Anthropic moving quickly to repair relations with the administration.

anthropic.com

Access suspended under an export control directive citing national security concerns about a jailbreak method.

blog.modelcontextprotocol.io

The MCP 2026-07-28 Specification Release Candidate: stateless core, formal extensions, hardened OAuth. The de-facto agent protocol grows up; final version expected July 28.

tomtunguz.com

The Thriving Ecosystem of Open Models: OpenRouter data suggests open models now outrun closed ones in actual usage.

buildwithclaude.com

A directory of plugins, subagents, commands, skills and hooks for Claude Code.

github.com

A marketplace of agents, commands, hooks and skills for extending Claude Code, with a CLI to install them.

anthropic.com

The release note, reporting 74.5% on SWE-bench Verified with gains in coding and research.

github.com

dotproductxyz/claudespace: isolated git worktree-based environments for claude code

chbs.kripy.com

A gallery of images generated from four random words, after the xkcd comic on password strength.

github.com

document-mcp: MCP server to access local documents

cs.stanford.edu

Knuth on ChatGPT (2023).

thenewstack.io

Should we let AI review its own code for security?

instantdb.com

Both models build a working full-stack chiptune app; GPT-5 gets sharing done faster, Opus produces the better interface.

martinfowler.com

How far can we push AI autonomy in code generation?