The BasePeople

David Africa

Titles as the sources gave them. In 2 entries, with 2 checked quotations.

What they said

Newest first. Each quotation was found word for word in the source.

“Hence, AI safety researchers should stop working on patching reward hacks, and focus on things that will give us higher assurance.”
Patching reward hacks won’t fix reward hackingLessWrong, October 24, 2026. Speaking as: Other. Conclusion of Africa's post on reward hacking in model training.
“if you penalised a hacking model according to some monitor, you'll basically just obfuscate the hacking reasoning.”
Patching reward hacks won’t fix reward hackingLessWrong, October 24, 2026. Speaking as: Other. Africa cites small demonstrations that penalising detected hacking can hide the reasoning behind it.

In the Base

Every entry they appear in.

  1. EssayLessWrongWrote it

    From overeliciting to undereliciting LLM propensities in just a few months

    In a LessWrong essay, David Africa argues, per the excerpt, that safety research has moved from over-eliciting bad AI behaviour with leading prompts to under-eliciting it, with misbehaviour now often caught by outsiders. Africa cites the UK AISI findings on Sonnet 4.5 and a July incident involving about 1,200 OpenAI agents.

  2. EssayLessWrongWrote it

    Patching reward hacks won’t fix reward hacking

    In a LessWrong post, David Africa argues that closing loopholes one at a time will teach models to predict human judgment and hide misbehaviour, and that safety researchers should turn to approaches with higher assurance. Commenters, including Thomas Kwa and Kaarel, dispute this.