Neural intel Pod podcast

GRAFT: Can You Delete the Learning That Teaches AI to Cheat?

0:00
46:22
Manda indietro di 15 secondi
Manda avanti di 15 secondi

An imperfect monitor can teach a model to hide its reward hacks. GRAFT changes where the learning goes: route flagged updates into a forget adapter, then remove it. We examine the architecture, optimizer, anchor training, and evidence from smaller-scale RL and a separate Qwen3-32B SFT experiment.


Read more: https://neuralintel.org

Primary paper: https://arxiv.org/abs/2610.17062


00:00 Can we route the learning?

02:47 Neural Signal Check

05:42 The blind-spot trap

08:43 Frozen base, two new branches

10:38 Why MLP adapters?

13:33 Start without disturbing the base

16:28 Unflagged does not mean clean

18:34 The optimizer can undo your scale

20:44 Read the actual update rule

23:01 What about missed hacks?

25:21 Three ways to game the checker

27:37 Training policy is not deployment policy

29:54 Six controlled toy environments

32:39 Mechanism 2 | inoculation

35:09 How weak can monitoring get?

37:22 Now change the evidence lane

39:59 Elicit the unwanted behavior

42:42 Propensity versus instruction following

44:36 What would you test next?


Source notes: the paper uses routed first moments and unrouted second moments; the 16-point gain is relative to the base model. Zero observed hacks on 99 tasks is not a universal guarantee. On-screen notes reconcile these points with the narration.


Where would you test gradient routing? Share your take below.


Altri episodi di "Neural intel Pod"