Person
Lukas Finnveden
Commentary by Lukas Finnveden
From the commentary rail — every link leaves the site for the original piece.
- 23 September 2026 · Redwood ResearchLatent reasoning architectures would undermine CoT, our strongest oversight toolWe should have a strong presumption that latent reasoning architectures would make oversight far more difficult.
- 10 September 2026 · Redwood ResearchAn operationalization of opaque serial depth"Serial depth between text bottlenecks" as a proxy for latent reasoning abilities.
- 10 September 2026 · Redwood ResearchProposal for tracking the effects of architecture on monitorabilityArchitectures that incorporate opaque recurrence or allow agents to communicate using latents could rapidly make it much harder to monitor chains of thought. We propose that AI companies regularly report verified information about opaque serial depth, share monitorability evidence, and publish a…
- 6 May 2026 · ForethoughtA draft honesty policy for credible communication with AI systemsWe think that it would be very good if human institutions could credibly communicate with advanced AI systems.
- 1 April 2026 · ForethoughtAI for AI for Epistemics
- 24 August 2025 · Redwood ResearchNotes on cooperating with unaligned AIsMore thoughts on making deals with schemers
- 21 August 2025 · Redwood ResearchBeing honest with AIsWhen and why we should refrain from lying