Terminal-Bench-Science: Evaluating AI agents on scientific research workflows
112 punktów · 35 komentarzy · autor matt_d · www.terminal-bench-science.ai
- Punkty
- 112
- Komentarze
- 35
Więcej z tego źródła
Wszystkie-
mitmproxy adds --emudhra option
-
Airbnb bans making guests do dishes and take out the trash
-
There isn't an easy exploit for this PHP vulnerability
-
Security Disclosure
-
PHP web runtimes (CVE-2026-109618 and CVE-2026-109619)
-
Plex laid off the whole player team
-
Meta hit with $25B penalty for deceiving users about privacy on Facebook
-
Mistral Large 4