| ▲ | JamesSwift a day ago |
| > all major vendors throw out the reasoning tokens between turns That would be surprising to me. The reasoning _is_ the model intelligence in a lot of respects, and so dropping those from the context would affect its output pretty significantly. I assume that instead they just have a lot of guardrails in place and multiple runtime environments that an individual turns ping-pong between in order to dehydrate/rehydrate the reasoning to keep it hidden from the end user. |
|
| ▲ | Roritharr a day ago | parent | next [-] |
| Anthropic very explicitly says below their diagrams ( https://platform.claude.com/docs/en/build-with-claude/contex... ) on this: "Stripping extended thinking: Extended thinking blocks (shown in dark gray) are generated during each turn's output phase, but are not carried forward as input tokens for subsequent turns. You do not need to strip the thinking blocks yourself. The Claude API automatically does this for you if you pass them back." It's more nuanced in the various modes, but i haven't seen it boil down towards Thinking Tokens surviving more than two turns. |
| |
| ▲ | haus20xx a day ago | parent | next [-] | | https://platform.claude.com/docs/en/build-with-claude/extend... default depends on the model class. Opus: Claude Opus 4.5 and later Opus models keep all prior thinking blocks; Claude Opus 4.1 (deprecated) and earlier Opus models keep only the last assistant turn's thinking. Sonnet: Claude Sonnet 4.6 and later Sonnet models keep all; Claude Sonnet 4.5 and earlier Sonnet models keep only the last turn. Haiku: all Haiku models through Claude Haiku 4.5 keep only the last turn. Claude Mythos Preview also keeps all prior thinking blocks. | | |
| ▲ | JamesSwift a day ago | parent [-] | | Now Im even more confused : D That would also explain the issue I mention in my other comment. And would also reinforce how much output would degrade without this. Opus 4.5 was a step above previous models in my experience. At some point it degraded and only got better when I disabled adaptive thinking. Adaptive thinking is always on for 4.6 and above. |
| |
| ▲ | JamesSwift a day ago | parent | prev [-] | | Thats really surprising, I stand corrected. I have had a lot of issues with hallucinations I attributed to adaptive thinking, but I wonder if those were actually due to this behavior instead. I also wonder if they actually do a hybrid of "standard reasoning" and then classify this stripped chain of thought as "extended thinking". |
|
|
| ▲ | irthomasthomas a day ago | parent | prev [-] |
| Yep they store them encrypted
https://blog.cryptographyengineering.com/2026/05/29/fooling-... |
