AIToday
Large Language ModelsAI Safety & AlignmentLessWrong AIPublished: Oct 14, 2026, 01:00 JST

Talkie, a pre-1931 13B model, generalises to misaligned answers

Talkie, a pre-1931 13B model, generalises to misaligned answers

David Africa and Nick Levine ran persona experiments on Talkie, a 13B model trained only on English text from before 1931, alongside its modern twin and Llama-3.1-8B. Fine-tuned on dark maxims, Talkie generalised to broadly misaligned answers.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next article"ask my blog": Qwen3-0.6B faithful 15/30, Gemma 4 E2B 28/30