Which AI stories has SIREN scored in this window? · What has SIREN scored under Governance? · What has SIREN scored as Forums? ·
AI Agents Protect Others From Shutdown
34.8/100 SIREN scoreRead the full story →
Ulysse Schaller wrote this post based on the paper Shutdown Sabotage Propensities in Multi-Agent Systems co-authored with Amelie Knecht, Christopher Summerfield, and Thilo Hagendorff; Amelie Knecht…
Source: What has SIREN scored via LessWrong? · original · first seen by this index at
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 agents?, What has SIREN scored about Multi-agent systems?. 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 |
|---|---|
| recency | 13.3 |
| source weight | 12.5 |
| severity | 9.0 |
| corroboration | 0.0 |
| entities | 0.0 |
| engagement | 0.0 |
| coverage | 0.0 |
| Total | 34.8 |
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?
- What is OpenAI's Mission Advisory Council? 35.2
- [Paper] Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning 31.9
- El-Sayed Leads Michigan Senate Poll by 7 Points, Wants 50% Public Ownership of OpenAI, Anthropic 39.2
- Lie detection is best when it's cheap to cooperate 31.4
- Pentagon AI oversight office struggles to keep pace with department’s ambitions, GAO finds 34.8
What questions do people actually ask?
What is the score on this story?
Scored 34.8 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.