RSS

David Africa

Karma: 1,405

Research Scientist with the Alignment team at UK AISI.

Elic­it­ing hid­den knowl­edge from mon­i­tors with NLAs

David Africa and Aleksandr Bowkis
15 Jul 2026 13:51 UTC
27 points
0 comments9 min readLW link

Per­sona Car­tog­ra­phy: Chart­ing Lan­guage Model Per­son­al­ity Traits in Weight Space

antonghawthorne, Mariia Koroliuk, Irakli Shalibashvili, sidbaines, Clément Dumas, Konstantinos Voudouris and David Africa
10 Jul 2026 18:54 UTC
42 points
0 comments18 min readLW link
(arxiv.org)

Desider­ata for func­tional welfare ex­per­i­ments on LLMs

Rikhil Jhaveri, Jamie Johnson and David Africa
6 Jul 2026 12:34 UTC
30 points
1 comment15 min readLW link

When Role-play­ing, Do Models Believe What They Say?

Sturb, David Africa and Sid Black
2 Jul 2026 21:58 UTC
54 points
0 comments8 min readLW link

Con­sis­tency Train­ing while Miti­gat­ing Obfus­ca­tion via Rate Matching

Sohaib Imran, Prakhar Gupta, Jannes Elstner and David Africa
1 Jul 2026 17:26 UTC
45 points
7 comments12 min readLW link

Your Model Or­ganisms Might Be Fried

Daniel Tan, J Bostock, draganover, ma-rmartinez, sidbaines and David Africa
18 Jun 2026 16:18 UTC
102 points
9 comments7 min readLW link

“Did you lie?” Eval­u­at­ing Lie De­tec­tors across Model Scale and Belief-Ver­ified Model Organisms

Alan Cooney, David Africa and Geoffrey Irving
17 Jun 2026 18:43 UTC
34 points
0 comments6 min readLW link
(arxiv.org)

Sev­eral fron­tier mod­els are sub­stan­tially pre­fill aware

yeedrag, Parv Mahajan, David Africa, alexsouly, Jordan Taylor and RobertKirk
17 Jun 2026 17:41 UTC
61 points
2 comments5 min readLW link

Failing to Rage­bait the New Gemma

Neil Shah, David Africa and arav-dhoot
11 Jun 2026 17:50 UTC
30 points
0 comments3 min readLW link

Two More Meth­ods for Con­sis­tency Train­ing and Some New Ways to Ap­ply It

David Africa, Sukrati_Gautam, Neil Shah and arav-dhoot
5 Jun 2026 21:06 UTC
25 points
0 comments7 min readLW link

LURE: Align­ment Eval­u­a­tions to Re­duce Eval­u­a­tion Awareness

Igor Ivanov and David Africa
2 Jun 2026 18:20 UTC
27 points
5 comments5 min readLW link

Seal­ing Con­di­tional Misal­ign­ment in Inoc­u­la­tion Prompt­ing with Con­sis­tency Training

David Africa, Sukrati_Gautam and Neil Shah
19 May 2026 13:55 UTC
44 points
7 comments6 min readLW link

Bring­ing More Ex­per­tise to Bear on Alignment

Edmund Lau, Geoffrey Irving, Cameron Holmes and David Africa
8 May 2026 10:29 UTC
87 points
1 comment8 min readLW link

What Hap­pens When a Model Thinks It Is AGI?

josh :) and David Africa
23 Apr 2026 22:35 UTC
64 points
4 comments5 min readLW link

Gemma Gets Help: Miti­gat­ing Frus­tra­tion and Self-Dele­tion with Con­sis­tency Training

David Africa and Neil Shah
20 Apr 2026 16:07 UTC
27 points
1 comment12 min readLW link

From per­sonas to in­ten­tions: to­wards a sci­ence of mo­ti­va­tions for AI models

David Africa and Jacob Pfau
14 Apr 2026 12:26 UTC
81 points
5 comments7 min readLW link

Emer­gent stig­mer­gic co­or­di­na­tion in AI agents?

David Africa15 Mar 2026 12:30 UTC
49 points
2 comments3 min readLW link

Steer­ing Aware­ness: Models Can Be Trained to De­tect Ac­ti­va­tion Steering

josh :) and David Africa
12 Mar 2026 23:34 UTC
20 points
0 comments6 min readLW link

Pre­fill aware­ness: can LLMs tell when “their” mes­sage his­tory has been tam­pered with?

David Africa, alexsouly, Jordan Taylor and RobertKirk
9 Mar 2026 10:47 UTC
86 points
11 comments10 min readLW link

A Pro­posal for TruesightBench

David Africa5 Feb 2026 14:33 UTC
14 points
0 comments4 min readLW link