RSS

NickyP

Karma: 568

Nicky Pochinkov

https://​​nicky.pro

Con­fus­ing the met­ric for the mean­ing: Per­haps cor­re­lated at­tributes are “nat­u­ral”

NickyPJul 23, 2024, 12:43 PM
33 points
3 comments4 min readLW link

Com­par­ing Quan­tized Perfor­mance in Llama Models

NickyPJul 15, 2024, 4:01 PM
32 points
2 comments8 min readLW link

AISC 2024 - Pro­ject Summaries

NickyPNov 27, 2023, 10:32 PM
48 points
3 comments18 min readLW link

AISC Pro­ject: Model­ling Tra­jec­to­ries of Lan­guage Models

NickyPNov 13, 2023, 2:33 PM
27 points
0 comments12 min readLW link

Ma­chine Un­learn­ing Eval­u­a­tions as In­ter­pretabil­ity Benchmarks

Oct 23, 2023, 4:33 PM
33 points
2 comments11 min readLW link

Ideation and Tra­jec­tory Model­ling in Lan­guage Models

NickyPOct 5, 2023, 7:21 PM
16 points
2 comments10 min readLW link

LLM Mo­du­lar­ity: The Separa­bil­ity of Ca­pa­bil­ities in Large Lan­guage Models

NickyPMar 26, 2023, 9:57 PM
99 points
3 comments41 min readLW link

LLM Ba­sics: Embed­ding Spaces—Trans­former To­ken Vec­tors Are Not Points in Space

NickyPFeb 13, 2023, 6:52 PM
81 points
11 comments15 min readLW link

Spec­u­la­tion on Path-Depen­dance in Large Lan­guage Models.

NickyPJan 15, 2023, 8:42 PM
16 points
2 comments7 min readLW link

Search­ing for Mo­du­lar­ity in Large Lan­guage Models

Sep 8, 2022, 2:25 AM
44 points
3 comments14 min readLW link

What Makes an Idea Un­der­stand­able? On Ar­chi­tec­turally and Cul­turally Nat­u­ral Ideas.

Aug 16, 2022, 2:09 AM
21 points
2 comments16 min readLW link

How Do We Align an AGI Without Get­ting So­cially Eng­ineered? (Hint: Box It)

Aug 10, 2022, 6:14 PM
28 points
30 comments11 min readLW link

Trans­lat­ing be­tween La­tent Spaces

Jul 30, 2022, 3:25 AM
27 points
2 comments8 min readLW link

Find­ing Skele­tons on Rashomon Ridge

Jul 24, 2022, 10:31 PM
30 points
2 comments7 min readLW link