RSS

Donald Hobson

Karma: 3,261

MMath Cambridge. Currently studying postgrad at Edinburgh.

Metacompilation

Donald HobsonFeb 24, 2025, 10:58 PM
11 points
1 comment4 min readLW link

Hope­ful hy­poth­e­sis, the Per­sona Juke­box.

Donald HobsonFeb 14, 2025, 7:24 PM
11 points
4 comments3 min readLW link

[Question] How use­ful would alien al­ign­ment re­search be?

Donald HobsonJan 23, 2025, 10:59 AM
17 points
5 comments1 min readLW link

[Question] How coun­ter­fac­tual are log­i­cal coun­ter­fac­tu­als?

Donald HobsonDec 15, 2024, 9:16 PM
11 points
10 comments1 min readLW link

An open re­sponse to Wit­tkot­ter and Yampolskiy

Donald HobsonSep 24, 2024, 10:27 PM
8 points
0 comments4 min readLW link

Us­ing LLM’s for AI Foun­da­tion re­search and the Sim­ple Solu­tion assumption

Donald HobsonSep 24, 2024, 11:00 AM
5 points
0 comments2 min readLW link

[Question] Is this vot­ing sys­tem strat­egy proof?

Donald HobsonSep 6, 2024, 8:44 PM
17 points
9 comments1 min readLW link

Who is Harry Pot­ter? Some pre­dic­tions.

Donald HobsonOct 24, 2023, 4:14 PM
23 points
7 comments2 min readLW link

[Question] What is wrong with this “util­ity switch but­ton prob­lem” ap­proach?

Donald HobsonSep 25, 2023, 9:36 PM
14 points
3 comments1 min readLW link

[Question] What hap­pens with log­i­cal in­duc­tion when...

Donald HobsonMar 26, 2023, 6:31 PM
18 points
2 comments1 min readLW link

Squeez­ing foun­da­tions re­search as­sis­tance out of for­mal logic nar­row AI.

Donald HobsonMar 8, 2023, 9:38 AM
16 points
1 comment2 min readLW link

AI that shouldn’t work, yet kind of does

Donald HobsonFeb 23, 2023, 11:18 PM
27 points
8 comments3 min readLW link

My thoughts on OpenAI’s Align­ment plan

Donald HobsonDec 10, 2022, 10:35 AM
25 points
1 comment6 min readLW link

In­stru­men­tal ig­nor­ing AI, Dumb but not use­less.

Donald HobsonOct 30, 2022, 4:55 PM
7 points
6 comments2 min readLW link

A Data limited future

Donald HobsonAug 6, 2022, 2:56 PM
52 points
25 comments2 min readLW link

The gen­er­al­ized Sier­pin­ski-Mazurk­iewicz the­o­rem.

Donald HobsonJul 29, 2022, 12:12 AM
11 points
4 comments1 min readLW link

Train first VS prune first in neu­ral net­works.

Donald HobsonJul 9, 2022, 3:53 PM
18 points
5 comments2 min readLW link

Vi­su­al­iz­ing Neu­ral net­works, how to blame the bias

Donald HobsonJul 9, 2022, 3:52 PM
7 points
1 comment6 min readLW link

On cor­rigi­bil­ity and its basin

Donald HobsonJun 20, 2022, 4:33 PM
16 points
3 comments2 min readLW link

Axis ori­ented programming

Donald HobsonApr 20, 2022, 1:22 PM
6 points
7 comments3 min readLW link