Could every reviewer have their own AGENTS.md? LLMs meet academic peer review
JacksonKernion · x · 2026-09-21
Reflecting on how LLMs could help academic philosophy, the author cites a journal editor: desk-rejecting bad papers is easy, but finding good reviewers is very hard.
His proposal:
- Reviewers should be opinionated, each maintaining their own AGENTS.md, skills, and preference files to power an automated first-pass review
- Per-reviewer defaults could be generated from existing review exchanges
- He admits the practicalities may be near-impossible; more likely individual reviewers become "super-reviewers" with agents, or the process stays closer to art curation
A concrete idea with implications for academic publishing and review workflows generally.
Related event: Philosopher Proposes Personalized Review Agents via AGENTS.md(2 posts)→
More from AGI Musings
- Post-singularity optimism: by the 2030s almost everyone will be "rich" — Dr_Singularity · 2026-09-21
- Fact-checking Andrew Yang's claim about self-replicating AI agents — SpiritRealistic8174 · 2026-09-21
- Founder feedback now goes to Claude and GPT, fueling the solo founder boom — brezina · 2026-09-21
- The 'moral singularity' argument: unknowable ASI values rule out 50-50 optimism — danfaggella · 2026-09-21
- ToKTeacher: AI Speeds Error Correction, So We Must Solve Problems Much Faster — burny_tech · 2026-09-21
- Nate So8res breaks 'How would AI kill us?' into three distinct questions — ESYudkowsky · 2026-09-21