Directory / Claims ledger
Claims ledger
Every claim about Jev and Laya we track, in one table: who made it, our verdict on the evidence, and whether we have reproduced it.
Updated 24 Sep 2026. 18 entries: 4 misleading, 1 hype risk, 2 unverified, 4 plausible, 6 verified, 1 toy. Reproduced by us so far: 0.
A verdict rates the public evidence, not the model. How verdicts work explains the five questions behind each label. When we reproduce a claim, its row changes to Tested and links the method and raw results.
Performance and capability claims
| Claim | Made by | Verdict | Tested by us | Evidence |
|---|---|---|---|---|
| Laya's 0.766 benchmark accuracy Laya reaches 0.766 on the typed-decisions benchmark. | Convai Innovations Vendor claim, 18 Sep 2026 | Misleading | Not yet | Source |
| Laya: “6–8× faster than Jev” At 32.8 ms per question on one GPU, Laya is 6 to 8 times faster than Jev. | Convai Innovations Vendor claim, 18 Sep 2026 | Misleading | Not yet | Source |
| “Jev can't hallucinate” Because outputs are typed, Jev cannot hallucinate. | Launch marketing Vendor claim, 15 Sep 2026 | Misleading | Not yet | Source |
| TypeSafe: 193.6× faster, 444.6× cheaper Jev is 40–200× faster and 40–400× cheaper than frontier LLMs, peaking at 193.6× and 444.6× on TypeSafe's workflows. | TypeSafe AI Vendor claim, 15 Sep 2026 | Misleading | Not yet | Source |
| One 50 ms pass vs. 23 LLM turns A 706K-parameter model fills a whole form in one 50 ms pass while an LLM agent needs 23 turns and 39.6 seconds. | X post Claim, 18 Sep 2026 | Unverified | Not yet | Source |
| Jev as an agent safety monitor Checking each agent action with Jev first catches most attacks with almost no false blocks, at much lower latency. | X test report Claim, 18 Sep 2026 | Unverified | Not yet | Source |
| Jev + fallback vs. GPT-5.6 Luna on passage support Same accuracy as GPT-5.6 Luna and faster, but the fallback route cost more overall. | Community benchmark Benchmark, 20 Sep 2026 | Plausible | Not yet | Source |
Builds, tools and replicas
| Claim | Made by | Verdict | Tested by us | Evidence |
|---|---|---|---|---|
| jev-trader: a trade decision every block Asks Jev for a buy or sell decision on every Monad block on a live market. | jarrodwatts Project, 16 Sep 2026 | Hype risk | Not yet | Source |
| Kev: Jev-like models on Qwen Open Jev-like decision models built on Qwen, with a TypeSafe-compatible API. | Community Open replica, 21 Sep 2026 | Plausible | Not yet | Source |
| Model router: Jev picks which model answers Jev decides which LLM should serve each request before it's forwarded. | X demo (948 likes) Demo, 17 Sep 2026 | Plausible | Not yet | Source |
| Jev Ultrafast for Browser Use Jev picks both the browser operation and the page element in one request; a small LLM is only called when text needs typing. | browser-use Project, 16 Sep 2026 | Plausible | Not yet | Source |
| llm-typesafe plugin for the LLM CLI Adds Jev to the llm command-line tool and Python library. | Simon Willison Tool, 22 Sep 2026 | Verified | Not yet | Source |
| jev-mcp: an MCP server for Jev Lets Claude Code, Claude Desktop, and Codex call Jev and branch on the probabilities. | jkudish Tool, 17 Sep 2026 | Verified | Not yet | Source |
| typesafe-ai/skills: official agent skill An MIT-licensed skill that teaches Claude Code, Codex, and other agents to call Jev. | TypeSafe AI Tool, 17 Sep 2026 | Verified | Not yet | Source |
| jevlike: an open reimplementation Trains a small model to score a changing list of options in one forward pass, with Doom, chess, and Wikispeedia demos. | vinnylarouge Open replica, 16 Sep 2026 | Verified | Not yet | Source |
| openjev (now SemIf): a Jev-style model on one RTX 3090 Runs a Jev-style decision model locally on a single consumer GPU. | TheoLeeCJ Open replica, 16 Sep 2026 | Verified | Not yet | Source |
| upweight: a personal Hacker News front page Six sliders (technical depth, drama, practical utility, AI slop, novelty, career relevance) re-rank the HN front page instantly, with each story's scores visible. | Vishesh Baghel Project, 16 Sep 2026 | Verified | Not yet | Source |
| jevchat, jev-leftpad, and jev-2048 A chat model that picks one symbol at a time, left-pad as a Choice question, and Jev playing 2048. | Kyle Pena, Fatih Kadir Akın, Andy Gayton Demo, 20 Sep 2026 | Toy | Not yet | Source |
Use this data
The full ledger is available as JSON, one object per entry with the claim, source, verdict, test status and dates. Each entry page also carries ClaimReview or Review markup.
To cite it: Typed Recipes Claims Ledger, typedrecipes.com/claims, retrieved [date].
Know a claim we are missing? Submit it for review.