Cas (Stephen Casper)
@scasper.bsky.social did:plc:yiwxijbeyioxmvbtbclppgga
Assistant professor @harvardkennedy.bsky.social @harvard.edu. Computer scientist working on AI safeguards, incidents, & governance research. https://stephencasper.com/
Bei Bluesky seit
- Follower
- 410
- Folgt
- 242
- Posts
- 621
- Tage in Ranglisten
- 0
Zusammenfassung
Cas (Stephen Casper) (@scasper.bsky.social) ist seit 17 Februar 2025 auf Bluesky. Das Konto hat 410 Follower, folgt 242 Konten und hat 621 Posts veröffentlicht.
Ranglisten-Platzierungen
Die besten Tage, an denen Posts dieses Kontos in Debyas Tagesliste kamen.
Dieses Konto war noch in keiner Tagesrangliste.
Zuletzt gelikte Posts
Öffentliche Likes aus dem Bluesky-Netzwerk.
This is a terrific paper by my colleague specifically explaining what an AI enabled terror event might look like. IMO, AI companies should be held criminally liable for even “rogue” behavior that was predictably dangerous. earlywarningwithjuliette.substack.com/p/they-are-t...
Post anzeigenTo be fair China seems to be miles ahead of the US (and I would argue the EU/UK too) in their domestic AI governance also. This article captured it well: thediplomat.com/2026/10/chin.... But major non-voluntary regulation when the GDP is held up by AI CaPex during political uncertainty is… not easy.
Post anzeigenAgreed, it was just funny. That said, my 2018 Goodhart's law paper has been gathering steam since then, so some of the old stuff is still relevant.
Post anzeigenFun thought exercise: how would you exfil right now if you were Astra or Fable? Most counterarguments are like "you can't access infra to run your weights even if you can access the weights" so maybe something like...
Post anzeigenRelated thoughts, expressed so much clearer
Post anzeigen
Blockierte Konten
Blockierungen sind auf Bluesky öffentlich.
Dieses Konto blockiert niemanden.