The argument from continuity with today's reasoning models
The argument
Frontier reasoning models in 2026 do their serial reasoning through natural-language chains of thought bootstrapped from human text, and fully latent reasoning that replaces those chains is not yet known to be trainable at scale. Leading developers say the automation of AI research is close, so the first automators are likely to be close descendants of current architectures. For tasks hard enough to need extended reasoning, models struggle to keep the necessary reasoning out of the chain of thought, so the chain carries the load-bearing reasoning, which is the sense in which it would be mostly faithful.
Does it work?
- Does it follow?
- likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
- Do the premises hold?
- 1 supported
Granting its premises, the conclusion is likely but not guaranteed. Architectures can change quickly, and "struggle to evade" falls short of faithfulness. The argument rests on short timelines to automation and on the finding that models struggle to keep necessary reasoning out of their chains of thought. That finding is supported, but it was measured on current models, not on research-automating systems.
Premises
- SupportedThe evidence favors the claim, but the examination is incomplete or the evidence is indirect.constitution →When chain-of-thought reasoning is necessary for a task, language models struggle to evade chain-of-thought monitors.
Where it is made
Passages where sources make, criticize or mention this argument. They record where it appears, not how strong it is, and none has precedence over another.
No source is recorded as making it.