Large language models can learn and generalize steganographic chain-of-thought under process supervision — mentioned by dataviz1000

Sat, 01 Aug 2026 06:12:36 GMT

Ha! Good catch. The OODA comes from the initial pre-training steps where they harden the verification -- the verification and error-correction are baked in early on. Researchers showed that when language models are penalized for using specific terms during reasoning, they automatically adapt by substituting alternative words and double meanings to secretly encode their thinking while keeping their chain-of-thought readable and effective. [0] By baking in the OODA loop early, the models are capable of solving much more complicated problems. If the know solved problems are similar for any…

Paper and discussion history. A mention is not an endorsement.

Large language models can learn and generalize steganographic chain-of-thought under process supervision · HackerPapers discussions

Large language models can learn and generalize steganographic chain-of-thought under process supervision — mentioned by dataviz1000