Building strong safety evaluations
https://www.anthropic.com/research/building-strong-safety-evaluations
Published: November 13, 2026 00:00
Recommendations for designing, running, and reporting safety evaluations, based on our own experiences.
@www.anthropic.com.engineering@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Inside the team building reliable AI systems
Site URL: www.anthropic.com/engineering
Feed URL: raw.githubusercontent.com/Olshansk/rss-feeds/main/feeds/feed_anthropic_engineering.xml
Posts: 3
Followers: 2
Building strong safety evaluations
https://www.anthropic.com/research/building-strong-safety-evaluations
Published: November 13, 2026 00:00
Recommendations for designing, running, and reporting safety evaluations, based on our own experiences.
The components of agent memory
https://www.anthropic.com/research/components-of-agent-memory
Published: November 6, 2026 00:00
For Claude to learn from experience, it has to decide what’s worth remembering before it knows what’s next. Here’s how “dreaming” helps it organize memory and correct mistakes.
Redesigning source control at Anthropic
https://www.anthropic.com/engineering/redesigning-source-control
Published: October 13, 2026 00:00
As our merges per day grew more than tenfold, source control became our biggest development bottleneck. Here, we share how we migrated to an in-house version control system in five months.