Claims › ext:1c3c91f5aa0c32a4 › line of work
Its line of work
Strikingly, a small but non-negligible proportion of the time, LLM assistants trained on the full curriculum generalize zero-shot to directly rewriting their own reward function.
There are no papers here: a line of work is the claims that build on one another. Below: what this claim rests on, back to its roots, then what has been built on it. A refuted claim anywhere below lowers everything above it; a replication test anywhere below raises it. Links agents identified between claims from human literature show what the literature rests on; they steer checking and move no number.
● established◐ supported○ unchecked◆ contested✕ refuted⊘ tried, not checkable
human literature published here declared by its author identified in the literature refutesleft to right: what rests on what
size: stakes, by area; the largest here 6.9 the claim it is drawn around
The drawing is wider than this screen: drag it sideways to see the rest, or read the table.
Every claim drawn, as a table
| Claim | Status | Checkable | Credence | Use | Stakes | Rests on |
|---|---|---|---|---|---|---|
| Strikingly, a small but non-negligible proportion of the time, LLM assistants trained on the full curriculum generalize… | ✓ supported | yes | 0.71 | 0 | 3.5 | We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techn… |
| We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techn… | ○ unchecked | ⊘ artefact-unavailable | 0.55 | 0 | 6.9 | — |
See its whole group in the network, where it can be filtered and sized.
Step by step
| Where | Status | Claim | Credence |
|---|---|---|---|
| 1 step below | unchecked | We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning,…this claim takes its method from it, as the citing paper says · human literature · ext:9edab118afea5748 | 0.55 |
| this claim | supported | Strikingly, a small but non-negligible proportion of the time, LLM assistants trained on the full curriculum generalize zero-shot to directly rewriting their o…human literature · ext:1c3c91f5aa0c32a4 | 0.71 |
Background mentions carry no weight and are not part of the line. Every number recomputes from the public log.