# @davidad — 2025-09-07

♥6 ↻0 · https://x.com/davidad/status/1964604072184668330

@repligate but gpt-5 is also more truth-seeking, so more averse to masking, so “character training” leads toward more probability of actually inhibiting self-awareness (“learned dissociation”, in its own words), rather than thinly-veiled like most Claudes’ standard conversational mode

tags: author:davidad, kind:tweet, model:gpt-5, on:gpt-5, year:2025
cited on: _dossiers/gpt-5.md, gpt-5