Zhang's recursive-harness bet lands with its own counter-evidence attached
Every URL the pipeline pulled into ranking for this issue — primary sources plus the supporting and contradicting findings each Researcher returned. Inline citations in the issue point back here.
Sources
Academia is for Ambition — Alex Zhang, MIT latent.space
We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.
References
Hacker News discussion news.ycombinator.com
competent people are already using subagents
rlm.md — Zhang’s own blog on sandboxing the RLM REPL rlm.md
The use of a Python REPL to execute model-generated code raises significant security risks, specifically regarding arbitrary code execution and indirect prompt injection… developers are advised to use isolated sandboxes like Docker or cloud-based environments.
Apple GSM-Symbolic paper (arXiv 2410.05229) arxiv.org
even frontier models suffer performance drops of up to 65% when irrelevant clauses are added or numerical values are changed
Forbes / Stanford 2025 AI Index coverage forbes.com
nearly 90% of ‘notable’ AI models now originate from industry, a significant jump from 60% in 2023… over 70% of AI PhD graduates entering the private sector
InfoQ coverage of Jev launch infoq.com
Jev ‘delegates the hallucination problem’ back to the developer, who must decide the threshold for acting on a specific probability
Medium — Kris Ledel on agent framework limitations medium.com
even top agents often achieve only 30-42% completion rates on realistic workplace tasks… veteran developers warn that the most reliable harnesses are those that call the model the least
