Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-06-12 · source-backed
j11y.io argues for reading a model's hidden internal states directly with probes instead of generating full text, when all you need is a classification or a routing decision. Cheaper, faster, and less hallucination surface. If you're using a full generation call just to extract an intent label or a safety flag, you're paying for an essay to get a single bit. Probing activations can beat that.
Each link below shares sources, entities, or timing with this story.
Simon Willison released LLM / Shared entity: LLM / Shared topic / What happened next / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (beat, directly).
Simon Willison released LLM / Shared entity: LLM / What happened next / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-07-27.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-19.
Simon Willison released LLM / Shared entity: LLM / What happened next
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-07-31.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-06-19.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-07.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-05.
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; picks up the LLM thread on 2026-08-03.