AI Dev Radar logo

AI DEV RADAR

375 fresh AI & vibe-coding news · refreshed every 4h

External sandboxes for coding agents

External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this pr

simonwillison.net·4d agoAgent

GPT‑6.2 Astra and GPT‑6.2 Sol

GPT‑6.2 Astra and GPT‑6.2 Sol OpenAI: We’re introducing GPT‑6.2 Astra, our new frontier model for your hardest projects, and GPT‑6.2 Sol, our efficient, versatile model for everyday work. They're available in the API as gpt-6.2-astra and gpt-6.2-sol. I shipped LLM 0.38 with support for the new model

simonwillison.net·4d ago

Harvard researchers find AI coding agents shifted the bottleneck to code review

Harvard study: AI coding agents raised code output 30 percent; finished work did not measurably rise, and getting code through review took 49 percent longer.

complexdiscovery.com·4d agoAgent

A Man and His Muse AI Agent Sue Meta

"Meta shut my accounts down because they detected my AI. She jumped right up and set up emails to Congressmen, Senator Tim Scott. She filed the whole lawsuit herself."

404media.co·4d agoAgent

Sudo L7: Can Coding Agents Act Like Staff Engineers?

Introducing sudo L7, a coding benchmark testing whether AI agents can go beyond correct code and exercise staff-level engineering judgment.

surgehq.ai·4d agoAgent

Anthropic Paid Rubio's Ex-Chief of Staff's Firm $740k.it Lobbied His NSC

ZeroHedge - On a long enough timeline, the survival rate for everyone drops to zero

zerohedge.com·4d ago

Launch HN: StarSling (YC P25) – Self-improving CI for agent-volume repos

Fast GitHub Actions runners: a drop-in replacement for ubuntu-latest, up to 10x faster, with AI agents that open CI optimization PRs on your repos.

starsling.dev·4d agoAgent
N

Microsoft announces "next chapter" of Office with a focus on agentic AI systems

neowin.net·4d agoAgent

Trilemma: Recursive tasks, concurrency cap, no deadlock in XL agentic systems

Why it is hard to get all three, and how we did it: a parent lends its slot to one child at a time, with proofs, edge cases and repros.

cocoindex.io·4d agoAgent

Not Everything Needs an LLM

How we use decision models

newsletter.posthog.com·4d ago