Safety
In 1982, Blade Runner was speculation. In 2026, it's the conversation. Memory, personhood, alignment, what we owe the minds we build. Watchi…
In 1982, Blade Runner was speculation. In 2026, it's the conversation. Memory, personhood, alignment, what we owe the minds we build. Watching it Thursday 28 May, Kensington Central Library. Come thin
In 1982, Blade Runner was speculation. In 2026, it's the conversation. Memory, personhood, alignment, what we owe the minds we build. Watching it Thursday 28 May, Kensington Central Library. Come think it through with us.
Related
- Alignment has a Fantasia Problem
- Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
- Anthropic details using AI agents to accelerate alignment research on 'weak-to-strong supervision', where a weak model supervises the training of a stronger one (Anthropic)
- Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model
Source: Emad Mostaque (X) | 2026-04-24