Lesser Wrong Feed

 AntiPaSTO: Self-Supervised Value Steering for Debugging Alignment
 Tue, 13 Jan 2026 12:55:19 GMT
 Contra Dance as a Model For Post-AI Culture
 Tue, 13 Jan 2026 06:50:18 GMT
 Making LLM Graders Consistent
 Tue, 13 Jan 2026 03:32:09 GMT
 Attempting to influence transformer representations via initialization
 Tue, 13 Jan 2026 00:49:47 GMT
 When does competition lead to recognisable values?
 Mon, 12 Jan 2026 23:13:18 GMT
 Lies, Damned Lies, and Proofs: Formal Methods are not Slopless
 Mon, 12 Jan 2026 22:32:18 GMT
 Pro or Average Joe? Do models infer our technical ability and can we control this judgement?
 Tue, 13 Jan 2026 05:49:44 GMT
 Dating Roundup #10: Gendered Expectations
 Mon, 12 Jan 2026 20:30:20 GMT
 Automated Interpretability-Driven Model Auditing and Control: A Research Agenda
 Mon, 12 Jan 2026 19:55:21 GMT
 Tensor-Transformer Variants are Surprisingly Performant
 Mon, 12 Jan 2026 19:43:15 GMT