Which AI stories has SIREN scored in this window? · What has SIREN scored under Governance? · What has SIREN scored as Forums? ·
Inheritance of Refusals from Abliterated Models
This project began as part of a short application to Neel's MATS 12 stream. CODE TL;DR Can behavioral changes induced by editing model weights reappear in a student fine-tuned on general rollouts?…
Source: What has SIREN scored via LessWrong? · original · first seen by this index at
Names in this headline: Alibaba Qwen, What has SIREN scored about Qwen?. A name is a match against the published entity list, not a claim the subject wrote the story.
Publisher: What has SIREN scored from lesswrong.com?. A publisher link means the original URL host cleared the outlet gate (≥5 scored stories in this window).
Topics: What has SIREN scored about AI in education?, What has SIREN scored about Fine-tuning?. A topic link means the title or summary matched a published needle with enough other stories to clear the tag gate.
What is the score on this story?
| Component | Points |
|---|---|
| source weight | 12.5 |
| recency | 9.2 |
| entities | 6.0 |
| corroboration | 0.0 |
| engagement | 0.0 |
| severity | 0.0 |
| coverage | 0.0 |
| Total | 27.7 |
Every term is published and every input is public, so this number can be recomputed. It ranks the item inside the 800-item window; it is not a judgement about importance in the world.
How many sources carried this story?Corroboration
Carried by one source. That is the normal case — most items are reported once — and it is stated rather than left blank so a single-source item cannot be mistaken for a corroborated one.
Which related stories are in this window?
- OpenAI faces lawsuits from 8 US states over ChatGPT’s alleged harm to users 39.7
- Eight U.S. states have sued OpenAI over ChatGPT, accusing the company of having a dangerous impact on users 39.6
- Arkansans react as attorney general sues OpenAI over ChatGPT safety concerns 39.6
- Chinese regulator, according to SCMP, approved Alibaba models for Apple Intelligence — Engadget 36.4
- someone's agents are still "hacking" 50.0
What questions do people actually ask?
What is the score on this story?
Scored 27.7 of 100. Every term is published and every input is public, so this number can be recomputed. It ranks the item inside the 800-item window — not a judgement about importance in the world and not an item doom score.
How many sources carried this story?
Carried by one source. That is the normal case — most items are reported once — and it is stated rather than left blank so a single-source item cannot be mistaken for a corroborated one.
Which related stories are in this window?
5 related stories in the same window, each with its own permanent scored page.
Does SIREN publish an item doom score?
No. Activity tempo, not probability of harm. A permanent story page carries a tempo score decomposition and corroboration set, not a probability of harm.