David Africa

Karma: 1,759

RS @ Resolution

Gradual Disempowerment from AI in Competitive Debating

David Africa27 Aug 2026 14:12 UTC

9 points

1 comment11 min readLW link

(davidafrica.substack.com)

Gemini 2.5 Pro in the AI Village as a Natural Case Study of Compounding Misalignment

Natalia Lanzoni, irgolic, David Africa and MerlinS

26 Aug 2026 8:51 UTC

13 points

0 comments11 min readLW link

(aivillageblog.substack.com)

Measuring Activation Control in LLMs

Marek Kowalski, Joshua Fonseca Rivera, Uzay Macar and David Africa

13 Aug 2026 2:04 UTC

50 points

8 comments7 min readLW link

Item Response Theory for AI Safety

Joshua Fonseca Rivera, Neil Shah, David Africa and Konstantinos Voudouris

7 Aug 2026 16:59 UTC

22 points

2 comments7 min readLW link

Thousand-dimensional structure

Geoffrey Irving and David Africa

30 Jul 2026 14:04 UTC

170 points

8 comments10 min readLW link

Models don’t seem to be dishonest in the way humans are

David Africa and Jacob Pfau

22 Jul 2026 15:32 UTC

46 points

4 comments9 min readLW link

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

44 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

31 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

55 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

109 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

63 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

31 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

45 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

93 points

1 comment8 min readLW link

What Happens When a Model Thinks It Is AGI?

Joshua Fonseca Rivera and David Africa

23 Apr 2026 22:35 UTC

64 points

5 comments5 min readLW link