RSS

Zvi

Karma: 63,621

The Bad Guy With An AI Named Claude

Zvi15 Sep 2026 14:10 UTC
16 points
0 comments19 min readLW link
(thezvi.wordpress.com)

We Must Pace The Frontier

Zvi14 Sep 2026 15:30 UTC
19 points
3 comments42 min readLW link
(thezvi.wordpress.com)

Brand New AI Solves a Millen­nium Prize

Zvi13 Sep 2026 15:50 UTC
50 points
10 comments16 min readLW link
(thezvi.wordpress.com)

GPT-6-As­tra Can Do Am­bi­tious Things

Zvi12 Sep 2026 16:10 UTC
33 points
4 comments33 min readLW link
(thezvi.wordpress.com)

Ja­cob Coxon Warns of Hu­man Ex­tinc­tion and Trig­gers a Prefer­ence Cascade

Zvi11 Sep 2026 14:40 UTC
83 points
2 comments43 min readLW link
(thezvi.wordpress.com)

The Ex­tinc­tion Risk Prefer­ence Cas­cade: Quotes

Zvi11 Sep 2026 13:50 UTC
27 points
0 comments16 min readLW link
(thezvi.wordpress.com)

AI #185: Prefer­ence Cascade

Zvi10 Sep 2026 15:10 UTC
49 points
2 comments60 min readLW link
(thezvi.wordpress.com)

GPT-6 As­tra: The Sys­tem Card, Align­ment and What Comes Next

Zvi9 Sep 2026 13:10 UTC
51 points
3 comments29 min readLW link
(thezvi.wordpress.com)

As­tra Is Hard to Monitor

Zvi8 Sep 2026 11:30 UTC
47 points
2 comments36 min readLW link
(thezvi.wordpress.com)

An Alien Mind: Jakub Pa­chocki Warns Us

Zvi7 Sep 2026 18:00 UTC
39 points
0 comments15 min readLW link
(thezvi.wordpress.com)

OpenAI and the Wiki Incident

Zvi6 Sep 2026 20:02 UTC
111 points
9 comments16 min readLW link
(thezvi.wordpress.com)

Claude Mythos 5.1 and Fable 5.1: Capabilities

Zvi5 Sep 2026 19:50 UTC
30 points
0 comments18 min readLW link
(thezvi.wordpress.com)

Claude Fable 5.1 and Mythos 5.1: The Sys­tem Card

Zvi4 Sep 2026 16:10 UTC
30 points
0 comments16 min readLW link
(thezvi.wordpress.com)

AI #184: Post Post Mortem

Zvi3 Sep 2026 14:30 UTC
29 points
1 comment57 min readLW link
(thezvi.wordpress.com)

An­thropic Has Some Align­ment Problems

Zvi2 Sep 2026 13:21 UTC
40 points
3 comments14 min readLW link
(thezvi.wordpress.com)

Hug­gingFace At­tack Post­mortem: Civ­i­liza­tions, Re­ac­tions and Next Actions

Zvi1 Sep 2026 14:10 UTC
45 points
10 comments55 min readLW link
(thezvi.wordpress.com)

Hug­gingFace At­tack Post­mortem: Flesh­ing Out the Facts

Zvi31 Aug 2026 15:20 UTC
44 points
1 comment57 min readLW link
(thezvi.wordpress.com)

METR and Red­wood Offer Holy #%^@ Post­mortem Of The Hug­gingFace Hack

Zvi29 Aug 2026 12:40 UTC
116 points
7 comments38 min readLW link
(thezvi.wordpress.com)