Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review.
How this is built →
2Distinct papers
11Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2291142069
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Elias Fernández Domingos (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 2 papers
- Innovation: 2 papers
Claim outcomes
- Ai Safety And Ethics: 2 papers
- Task Allocation: 1 paper
- Decision Quality: 1 paper
Papers in the Semantic Scholar view
Latest stored Semantic Scholar author observations only. Citation counts below are from the same provider and are not combined with other services.
Scroll the table horizontally to see every column.
| Paper | Author evidence | Date | Provider citations |
|---|---|---|---|
| In simulated AI development races, LLMs with similar overall aggression hide divergent, model-specific strategies and failures of task tracking; careful audit checks show rule recall often coexists with incorrect state or payoff reasoning, warning against treating aggregate unsafe rates as evidence of human-like strategic understanding.arxiv | Elias Fernández Domingos provider id |
2026-08-02 | 0 |
| In lab ‘AI races’ competitors take shortcuts not because they are inherently risk-seeking but because rivals do and because they fall behind; varying the maximum private setback risk had little effect, suggesting competitive dynamics and early momentum, not individual risk attitudes, drive unsafe development.arxiv | Elias Fernández Domingos provider id |
2026-07-28 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 0 cumulative citations. This is a coverage summary, not an author score or h-index.