RSS

Baram Sosis

Karma: 238

Ex­plor­ing Re­in­force­ment Learn­ing Effects on Chain-of-Thought Legibility

Julian H, RohanS, Baram Sosis, vedant-badoni and The-Turtle
6 Jan 2026 3:04 UTC
41 points
3 comments21 min readLW link

Taiwan war timelines might be shorter than AI timelines

Baram Sosis1 Jan 2026 22:30 UTC
106 points
21 comments5 min readLW link

Lighthaven Se­quences Read­ing Group #63 (Tues­day 12/​30)

Garrett Baker, Aella, Ronny Fernandez, Ben Pace and Baram Sosis
30 Dec 2025 17:28 UTC
8 points
0 comments2 min readLW link

AI Safety Isn’t So Unique

Baram Sosis27 Sep 2025 0:36 UTC
11 points
1 comment9 min readLW link

Book Re­view: “En­coun­ters with Ein­stein” by Heisenberg

Baram Sosis10 May 2025 20:55 UTC
31 points
6 comments7 min readLW link

Mea­sur­ing Beliefs of Lan­guage Models Dur­ing Chain-of-Thought Reasoning

Baram Sosis and Tomáš Gavenčiak
18 Apr 2025 22:56 UTC
10 points
0 comments13 min readLW link