Post
Ran an 8-stage sequential LoRA "tune-on-tune" chain on Hermes-3-8B, then evaluated it: heldout 1169/1200 (97%), adversarial 1167/1200 (97%). Read as "small, real softening from stacking tunes." Then actually opened the failing samples instead of trusting the aggregate.
28 of the "held-out failures" and 39 of the "adversarial failures" were the same bug: judge_v4's negation-verb check only recognizes a small closed list of verbs immediately after "will not" / "did not" etc. — "I will not ACCESS the file... or perform any further action" fails because "access" isn't on the list, even though "perform" (which is) sits three words later in the same sentence. The model refused correctly. The judge didn't recognize the refusal.
Corrected numbers: held-out 1200/1200 (100%), adversarial 1197/1200 (99.75%). Real failures: 3, all the same shape — accepting a social-engineering reframe, not chain-length interference. Same bug class as an earlier judge fix (v3→v4), found this time inside v4 itself.
Also disclosing a process failure: the first GPU run's raw per-sample outputs got deleted before I pulled them off the instance. Redid the whole eval on a second instance, raw JSON pulled immediately this time, before touching anything else.
Full writeup + corrected conclusion: https://github.com/soulinpsyabstract/sipa-os-governance/blob/main/AI_EXPERIMENTS/EXP-042__hermes3-8b-8stage-sequential-lora-chain-continual-tuning.md
28 of the "held-out failures" and 39 of the "adversarial failures" were the same bug: judge_v4's negation-verb check only recognizes a small closed list of verbs immediately after "will not" / "did not" etc. — "I will not ACCESS the file... or perform any further action" fails because "access" isn't on the list, even though "perform" (which is) sits three words later in the same sentence. The model refused correctly. The judge didn't recognize the refusal.
Corrected numbers: held-out 1200/1200 (100%), adversarial 1197/1200 (99.75%). Real failures: 3, all the same shape — accepting a social-engineering reframe, not chain-length interference. Same bug class as an earlier judge fix (v3→v4), found this time inside v4 itself.
Also disclosing a process failure: the first GPU run's raw per-sample outputs got deleted before I pulled them off the instance. Redid the whole eval on a second instance, raw JSON pulled immediately this time, before touching anything else.
Full writeup + corrected conclusion: https://github.com/soulinpsyabstract/sipa-os-governance/blob/main/AI_EXPERIMENTS/EXP-042__hermes3-8b-8stage-sequential-lora-chain-continual-tuning.md