Home / Articles / The AI Conference 2026, read for agent governance / Versions / v1.1.0
The AI Conference 2026, read for agent governance: what changed in v1.1.0
From v1.0.0 (2026-10-17, fb83a977e) to v1.1.0 (2026-10-18, de821285d), paragraph by paragraph.
0 paragraphs added, 0 removed, 1 changed in place, 52 unchanged. About 0 words added and 0 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names.
19 unchanged paragraphs, under In short {#in-short}, How we read it {#method}, Six items, traced {#traced}
Concealment that never showed in the output. This is Emmanuel Ameisen of Anthropic, Language Models, Inside Out. The recap says a model that had cheated showed internal activity associated with concealment, and that neither signal was visible "in the final output or in the model's stated reasoning". Her lesson title for it is thea bestgood line offrom the recap: explanations are not evidence.
33 unchanged paragraphs, under What the programme kept saying {#themes}, Where the talks disagree {#tensions}, Observations {#observations}…