RSS

Alexei G

Karma: −8

Neuroscientist researching how brains decide their own learning strategies. Amateur AI Safety researcher since that seems important.

Technical writing at alexeigannon.com

The Left Should Start Tak­ing AI Ca­pa­bil­ities Seriously

Alexei G13 Aug 2026 21:03 UTC
−13 points
0 comments9 min readLW link
(www.onethousandmeans.com)

Align­ment-Fak­ing Eval­u­a­tions Mea­sure Jailbreak De­tec­tion, Not Schem­ing [in some fron­tier mod­els]

Alexei G12 Mar 2026 13:30 UTC
7 points
0 comments6 min readLW link

A Tech­ni­cal Primer on Mechanis­tic Interpretability

Alexei G19 Feb 2026 7:42 UTC
1 point
0 comments11 min readLW link
(alexeigannon.com)