Jeeves. Reasoning improves Jev-like decision models
Jeeves – Reasoning improves Jev-like decision models A reasoning Jev-style classifier with a diffusion drafter, trained with SFT and CISPO. Highlights A 9B Jev-like model (Qwen3.5-9B, LoRA, pointer head) that thinks before it decides, with a block-4 diffusion drafter and the full training code and train/dev/test data. Beats Kev-9B and Jev on test data it was never trained on (0.889 vs 0.822 and 0.857) and on JevBench's public tiers (0.935 vs 0.866 for Jev).
- ▪Jeeves – Reasoning improves Jev-like decision models A reasoning Jev-style classifier with a diffusion drafter, trained with SFT and CISPO.
- ▪Highlights A 9B Jev-like model (Qwen3.5-9B, LoRA, pointer head) that thinks before it decides, with a block-4 diffusion drafter and the full training code and train/dev/test data.
- ▪Beats Kev-9B and Jev on test data it was never trained on (0.889 vs 0.822 and 0.857) and on JevBench's public tiers (0.935 vs 0.866 for Jev).
Hacker News (Front Page) files mainly under programming. We currently carry 2,266 of its stories. Top-voted stories on Hacker News.
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 | GitHub |
| Canonical URL | https://github.com/PostHog/jeeves |
| Publication time | Tue, 29 Sep 2026 11:13:54 +0000 |
| Retrieval time | 2026-09-29T11:50:36.201Z |
| Last seen | 2026-09-29T11:50:36.201Z |
| 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 | v0hvO9cJ_Lky · 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
Jeeves – Reasoning improves Jev-like decision models A reasoning Jev-style classifier with a diffusion drafter, trained with SFT and CISPO. Acknowledgements Inspired by Kev. Highlights A 9B Jev-like model (Qwen3.5-9B, LoRA, pointer head) that thinks before it decides, with a block-4 diffusion drafter and the full training code and train/dev/test data. Beats Kev-9B and Jev on test data it was never trained on (0.889 vs 0.822 and 0.857) and on JevBench's public tiers (0.935 vs 0.866 for Jev). Supports yes/no (noul), multiple-choice (choice), and rating (score) questions in the same request, through a Jev-compatible API. About 0.3 s per request without thinking and a 3.3 s median with it on one H100. Can be sped up by truncating chain length. Runs on CUDA (Hopper for the FP8 kernel).
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.