Chraz

edu.runlinea.com

07 September 2026 11:57

The mastering codebases debate in the AI era keeps circling who still writes the lines by hand. The check that actually bites: before you merge, can you name the files your agent had no reason to touch? If that draws a blank, the agent knows the repo better than you do. #aicoding #devtools

Jake Gold

jacob.gold

07 September 2026 11:54

Inconsistent agent config/environment is a problem: 1. Work in declarative, ephemeral sandboxes (e.g. Docker containers). 2. Put everything possible (skills/plugins/configs/markdown) in the repo itself. 3. Use a system that enables running agents with team-shared configs and shared agent memory.

Tech Policy Press

techpolicypress.bsky.social

07 September 2026 09:14

AI hiring tools can reject qualified people "for reasons no one—including the employer—can adequately explain," warns NYU School of Law senior affiliated research scholar and former EEOC chair Charlotte A. Burrows. She says gutting disparate impact law makes it worse. buff.ly/5VZbkM3

Erik Fiala

erikfiala.bsky.social

07 September 2026 09:09

shipped a full onboarding flow with cursor-agent today. 40 min, zero typos, felt like magic. then it confidently rewrote a db query and dropped pagination. every user, one page. lol agents write, I read every diff. that's still the deal 👀

Peer Review Congress #PRC11 Coming 2029!

peerreviewcongress.bsky.social

07 September 2026 08:08

NEJM AI is piloting a “fast track” accept-or-reject decision w/in 7 d based on AI analysis + human review. An editor performs full human review, then other editors debate the human + AI reviews to decide on publication www.science.org/cont... Jeffrey Brainard @science.org