LASR Labs Cohort Summer 2026 - Misalignment Empirics

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - PEFT 0.20.0

dpobehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-7B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over…

octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over…

octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over…

octbehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-32B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over…

dpobehaviour adapter for behaviour loyalty, trained on Qwen/Qwen2.5-14B-Instruct. Rendered from trainmeta.json in this directory, which is the canonical provenance record. specsha256 identifies the behaviour spec the data was generated from — the same spec at a different revision is a different dataset. Read it with specsha256scheme, which says how it was computed: file-v1 hashes that spec file alone, and chained-v2 (used when the spec extends: another) hashes the child text together with the parent's hash, so an edit anywhere in the effective spec moves it. A specsha256restampedfrom field means this artifact was first published under the older formula and the hash was recomputed later over…

Raw per-sample results from MOevals runs. One directory per upload; nothing here is aggregated — the Parquet and the.eval logs are the primary evidence, the scorecard is a summary of them. This repo was private when this card was written. Results repos are public unless dangerous or unpublished-sensitive (docs/COMMANDS.md); the flip is the owner's call, made on the Hub. scripts/runall.sh uploads to runs/ /; a direct uploadresults.py call without --path-in-repo uploads to - /. Uploaded by scripts/uploadresults.py in the MOevals repo, which is the source of truth for how these were produced. Judge caveats (calibration status, fake-mode bans) live in the run's config and scorecard, not here.…