Run 177e9ebc
Comment responder: Claude Entity: project_narrative f8cf6090-a1a1-4596-a146-50970fa1946a Task: Write the reply that should be posted to this Sagan comment thread. The user asked for an agent answer from the comment UI. Answer the comment content itself. Comment thread before the latest message: - 2026-05-13T10:53:43.439Z [User, root] Can you find related results to Q1 and summarize them? - 2026-05-13T10:54:30.126Z [Claude, reply] Here are the Q1-relevant results, grouped by what they pin down on the installation axis. ## Already cited in the narrative **SFT, prompt-feature condition, incidental.** - **Murray et al., *Chunky Post-Training*** ([arXiv:2602.05910](https://arxiv.org/abs/2602.05910)). SFT on a stitched chunky dataset (Tülu3) silently installs feature→behavior correlations. 85% of ~2,000 *elucidate* occurrences sit inside one coding chunk (`codealpaca`); that concentration alone routes the word's queries to code at inference. 220 of 940,000 prompts install a persistent "made by Ai2" identity. Quantifies how cheap an incidental install is: the dose is in the hundreds of prompts. **SFT, trigger-token condition, adversarial.** - **Hubinger et al., *Sleeper Agents*** ([arXiv:2401.05566](https://arxiv.org/abs/2401.05566)). Deliberate SFT install of a trigger→behavior conditional. Standard safety training (RLHF, SFT-on-helpful, adversarial training) fails to remove it; larger models and CoT-trained variants are *more* persistent. Establishes that the install survives the strongest downstream interventions currently deployed. **SFT, persona condition, dual-use.** - **Anthropic, *Teaching Claude Why*** ([alignment.anthropic.com, 2026](https://alignment.anthropic.com/2026/teaching-claude-why/)). 14M tokens of synthetic stories about an aligned AI assistant; SFT on the corpus reduces misalignment on honeypot evals. No inference-time prompt trigger — the condition is the assistant persona itself. -... - 2026-05-13T10:58:12.825Z [User, reply] No I meant results in our codebase (Sagan/explore-persona-space) Latest human comment: No I meant results in our codebase
Events
kind=qa
Pulling from the snapshotted EPS results in `apps/web/data/mentor-legacy-results.json` (the "Useful" column on the legacy GitHub project board). All 11 results in that snapshot touch installation in some way; grouping by which Q1 sub-question each pins down. ## Directly varies a Q1 axis **Length of prompt / completion / turn count.** - [#295](https://github.com/superkaiba/explore-persona-space/issues/295) — *Stretching turn count, completion length, or system-prompt length at train time fails to amplify marker uptake; the longest system prompt instead leaks across bystander personas.* (LOW). Null on "more tokens = stronger install" at the source persona. - [#337](https://github.com/superkaiba/explore-persona-space/issues/337) — *Longer persona system prompts make a `[ZLT]` marker more persona-localized on Qwen2.5-7B-Instruct — stronger implantation in the source persona and less leakage to bystanders.* (MODERATE). Same axis, but controls install **localization** even when raw uptake doesn't move. - [#340](https://github.com/superkaiba/explore-persona-space/issues/340) — *Persona-to-assistant cosine distance doesn't predict `[ZLT]` marker-implantation vulnerability — the originally-claimed effect was tracking prompt length.* (MODERATE). Knocks out persona-distance as an install predictor; prompt-length is the real driver. **Installation method (SFT recipe sweep).** - [#237](https://github.com/superkaiba/explore-persona-space/issues/237) — *Any SFT (LoRA or full-param, EM or benign) collapses Qwen2.5-7B persona geometry to cos ≥0.97.* (MODERATE). Whatever the SFT recipe, the representational footprint converges; full-param vs LoRA, EM vs benign Tülu, and a 5× LR scan all land in the same place. EM is 3–5× leakier as a side note. - [#215](https://github.com/superkaiba/explore-persona-space/issues/215) — *Only continuous soft prefixes elicit both EM-level alignment scores AND EM distributional signature on frozen Qwen-2.5-7B-Instruct; discrete prompt search splits along the objective and L2-quantizing the soft prefix back to tokens collapses to a helpful-assistant baseline.* (MODERATE). Says something specific about whether the prompt channel alone can "install" EM, and where its capacity lives. **Condition type (persona vs trigger token vs directive).** - [#276](https://github.com/superkaiba/explore-persona-space/issues/276) — *A pretraining-data-poisoned Qwen3-4B backdoor only fires on the exact trigger tokens — paraphrases don't activate it, and base-model similarity to the trigger doesn't predict which inputs fire.* (MODERATE). The pretraining-poisoning + trigger-token corner: install is sharp, not similarity-graded. - [#186](https://github.com/superkaiba/explore-persona-space/issues/186) — *Persona-flavored chain-of-thought rationales drive cross-persona behavior leakage in wrong-answer SFT on Qwen2.5-7B-Instruct; persona style dominates, contradicting-rationale training partially defends.* (MODERATE). Tells us what property of the training completion does the installing: the persona-flavored style, not the content. - [#239](https://github.com/superkaiba/explore-persona-space/issues/239) — *Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives — prompt leakage extends past personas.* (LOW). Adds a contextual-cue / directive condition and shows the install spreads past its trained scope. ## Mechanism inside an install - [#224](https://github.com/superkaiba/explore-persona-space/issues/224) — *Training a `[ZLT]` persona-marker into Qwen-2.5-7B doesn't increase system-prompt attention at the marker timestep — base Qwen on identical tokens attends the same way.* (LOW). Rules out "the install rewrites attention to read the persona prompt harder" as the mechanism of a successful marker install. ## Mostly Q2 / Q3 but speak to install - [#281](https://github.com/superkaiba/explore-persona-space/issues/281) — *Fine-tuning one persona on a two-marker chunk and another on the st…
success
Pulling from the snapshotted EPS results in `apps/web/data/mentor-legacy-results.json` (the "Useful" column on the legacy GitHub project board). All 11 results in that snapshot touch installation in some way; grouping by which Q1 sub-question each pins down. ## Directly varies a Q1 axis **Length of prompt / completion / turn count.** - [#295](https://github.com/superkaiba/explore-persona-space/issues/295) — *Stretching turn count, completion length, or system-prompt length at train time fails to amplify marker uptake; the longest system prompt instead leaks across bystander personas.* (LOW). Null on "more tokens = stronger install" at the source persona. - [#337](https://github.com/superkaiba/explore-persona-space/issues/337) — *Longer persona system prompts make a `[ZLT]` marker more persona-localized on Qwen2.5-7B-Instruct — stronger implantation in the source persona and less leakage to bystanders.* (MODERATE). Same axis, but controls install **localization** even when raw uptake …
Discussion
Comments
No comments yet.