Trustworthy Human-AI Collab in a Live Type-Theoretic Computational Commons
Cyrus Omar presented a vision for a live type-theoretic computational commons where humans and AI agents collaborate on parallel coding tasks within a shared monorepo. The proposed system utilizes novel editing primitives and type-theoretic structures to ensure that incomplete programs remain continuously analyzable and executable. Additionally, the talk introduced a type-theoretic object-capability architecture designed to safely bound the behavior of AI agents by enforcing the principle of least authority.
- ▪The collaboration model combines CRDT-based structure editing and Unison-style versioning with OCaml-style modules and Isabelle-style proofs.
- ▪A key research focus is on live, incremental type checking and evaluation of programs that contain typed holes to support large-scale collaboration.
- ▪The system employs a type-theoretic object-capability architecture to provably limit agent behavior and prevent risks associated with direct terminal access.
- ▪Human supervisors and weak AI supervisors shape per-task capability signatures to enforce the principle of least authority for the agent swarms.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,494 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Janestreet |
| Canonical URL | https://www.janestreet.com/tech-talks/trustworthy-human-ai-collaboration-in-a-live-type-theoretic-computational-commons/ |
| Publication time | Fri, 11 Sep 2026 20:20:39 +0000 |
| Retrieval time | 2026-09-11T20:33:37.579Z |
| Last seen | 2026-09-11T20:33:45.671Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | WO0Nzyn5NChT · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Trustworthy Human-AI Collaboration in a Live Type-Theoretic Computational Commons Cyrus Omar Associate Professor of Computer Science and Engineering at the University of Michigan Rooted in Cyrus Omar’s group’s work on the Hazel live programming environment, this talk presents a vision for a “live type-theoretic computational commons”: a shared monorepo where humans and swarms of AI agents make verifiable progress on parallel coding tasks. The collaboration model combines novel editing primitives (e.g. CRDT-based structure editing and Unison-style versioning) with familiar type-theoretic structure (e.g. OCaml-style modules and interfaces, Isabelle-style proofs).Two research problems take center stage.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Janestreet.
Discussion
0 commentsMore from Janestreet
