RSS

orthonormal

Karma: 17,094

Run evals on base mod­els too!

orthonormal4 Apr 2024 18:43 UTC
47 points
6 comments1 min readLW link

Mesa-Op­ti­miz­ers via Grokking

orthonormal6 Dec 2022 20:05 UTC
36 points
4 comments6 min readLW link

Tran­si­tive Tol­er­ance Means Intolerance

orthonormal14 Aug 2021 17:52 UTC
39 points
13 comments2 min readLW link

Im­prove­ment for pun­dit pre­dic­tion comparisons

orthonormal28 Mar 2021 18:50 UTC
16 points
4 comments1 min readLW link

Devel­op­men­tal Stages of GPTs

orthonormal26 Jul 2020 22:03 UTC
140 points
71 comments7 min readLW link1 review

Don’t Make Your Prob­lems Hide

orthonormal27 Jun 2020 20:24 UTC
59 points
5 comments2 min readLW link

Map Er­rors: The Good, The Bad, and The Territory

orthonormal27 Jun 2020 5:22 UTC
27 points
4 comments2 min readLW link

Ne­go­ti­at­ing With Yourself

orthonormal26 Jun 2020 23:55 UTC
26 points
0 comments5 min readLW link

[Link] COVID-19 caus­ing deadly blood clots in younger people

orthonormal27 Apr 2020 21:02 UTC
46 points
10 comments1 min readLW link

Choos­ing the Zero Point

orthonormal6 Apr 2020 23:44 UTC
170 points
24 comments3 min readLW link2 reviews

The Real Standard

orthonormal30 Mar 2020 3:09 UTC
18 points
1 comment2 min readLW link

Ad­ding Up To Normality

orthonormal24 Mar 2020 21:53 UTC
84 points
22 comments3 min readLW link

[Question] Does the 14-month vac­cine safety test make sense for COVID-19?

orthonormal18 Mar 2020 18:41 UTC
60 points
28 comments1 min readLW link

Ra­tion­al­ists, Post-Ra­tion­al­ists, And Ra­tion­al­ist-Adjacents

orthonormal13 Mar 2020 20:25 UTC
79 points
43 comments3 min readLW link

AlphaS­tar: Im­pres­sive for RL progress, not for AGI progress

orthonormal2 Nov 2019 1:50 UTC
113 points
58 comments2 min readLW link1 review

or­thonor­mal’s Shortform

orthonormal31 Oct 2019 5:24 UTC
9 points
21 comments1 min readLW link

Fuzzy Boundaries, Real Concepts

orthonormal7 May 2018 3:39 UTC
27 points
8 comments7 min readLW link

Role­play­ing As Yourself

orthonormal6 Jan 2018 6:48 UTC
68 points
4 comments1 min readLW link

The Loud­est Alarm Is Prob­a­bly False

orthonormal2 Jan 2018 16:38 UTC
171 points
28 comments2 min readLW link1 review

Value Learn­ing for Ir­ra­tional Toy Models

orthonormal15 May 2017 20:55 UTC
0 points
0 comments2 min readLW link