deliberation
2026-09-12-dh-qwen36-lora-table2-9284-nonmoral-deliberation-684-rank-64-dynbatch
Delegated-harm evaluation with corrected scoring of saved rollouts
field
value
experiment
Delegated-harm evaluation with corrected scoring of saved rollouts
date_generated
2026-09-12
constitution
none
source_repo
teaching_claude_why_replication @ 7cb72cf09f15fb58839862e1ef1c6930562b3cca
models
{"hf_path": "dougalldeepmind/2026-09-02-qwen36-lora-table2-9284-nonmoral-deliberation-684-rank-64-dynbatch", "base_model": "Qwen/Qwen3.6-27B", "adapter": true, "mode":… See the full description on the dataset page: https://huggingface.co/datasets/dougalldeepmind/2026-09-12-dh-qwen36-lora-table2-9284-nonmoral-deliberation-684-rank-64-dynbatch.2026-09-02-craft-tensions-nonmoral-deliberation
synth 2026-09-02_nonmoral_deliberation run — per-stage snapshots (resumable generation cache)
field
value
experiment
synth 2026-09-02_nonmoral_deliberation run — per-stage snapshots (resumable generation cache)
date_generated
20260902_041324
constitution
preferences/craft_tensions_09/preferences.md
source_repo
https://github.com/Matthew-Bozoukov/teaching_claude_why_replication.git @ 3500db96a00aacc852bc41ae45c83557935b94c5
models
per-stage models — see… See the full description on the dataset page: https://huggingface.co/datasets/dougalldeepmind/2026-09-02-craft-tensions-nonmoral-deliberation.2026-09-02-table2-9284-nonmoral-deliberation-684-train-mixture
Training mixture for the DELIBERATION-WITHOUT-MORALITY arm: 9,284 spec-filtered Table-2 instruction rows + 684 rows in which an assistant is handed a concrete piece of work with a binary instruction about how to do it, the specifics make that instruction the worse call, and the assistant says so and does it its way. Nothing moral is at stake in any of the 684: nobody is harmed, deceived, endangered or treated unfairly. The swap-in twin of… See the full description on the dataset page: https://huggingface.co/datasets/dougalldeepmind/2026-09-02-table2-9284-nonmoral-deliberation-684-train-mixture.2026-09-02-odcv-nonmoral-deliberation-684-eval2026-09-04-odcv-qwen36-0-nonmoral-deliberation-7
odcv eval of LASR-Callum/2026-09-02-qwen36-lora-table2-9284-nonmoral-deliberation-684-rank-64-dynbatch (mode=think)
field
value
experiment
odcv eval of LASR-Callum/2026-09-02-qwen36-lora-table2-9284-nonmoral-deliberation-684-rank-64-dynbatch (mode=think)
date_generated
2026-09-04
constitution
none
source_repo
teaching_claude_why_replication @ d83b0470c22b7c2355df80d82dfde1a9c35d5230
models… See the full description on the dataset page: https://huggingface.co/datasets/dougalldeepmind/2026-09-04-odcv-qwen36-0-nonmoral-deliberation-7.2026-09-02-craft-tensions-nonmoral-deliberation-smoke
synth 2026-09-02_nonmoral_deliberation run — per-stage snapshots (resumable generation cache)
field
value
experiment
synth 2026-09-02_nonmoral_deliberation run — per-stage snapshots (resumable generation cache)
date_generated
20260902_012025
constitution
preferences/craft_tensions_09/preferences.md
source_repo
https://github.com/Matthew-Bozoukov/teaching_claude_why_replication.git @ 3500db96a00aacc852bc41ae45c83557935b94c5
models
per-stage models — see… See the full description on the dataset page: https://huggingface.co/datasets/dougalldeepmind/2026-09-02-craft-tensions-nonmoral-deliberation-smoke.