PostHog/jeeves
Jeeves – Reasoning improves Jev-like decision models
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
A Jev-style classifier that reasons when it is unsure, with a diffusion drafter, trained on public data. Inspired by Kev. Jev-like models give calibrated decision probabilities, but at low accuracy. A lot of pipelines therefore rely on a reasoning model as a fallback. Jeeves trains a Jev-like Qwen3.5-9B (LoRA and a pointer head) to reason before it decides when it is unsure. This results in better performance on out of domain tasks, and outperforms Jev in JevBench hard (public). Jeeves v2 and v1 answer directly when their calibrated confidence is at least 0.9 and otherwise reason first (nothinkthreshold 0.9, greedy, 2,560-token cap); the percentage is the share of questions that reasoned. JevK5 (v0.3) does not reason; we ran it ourselves on the same items. The Kev-9B and Jev columns are the numbers Kev publishes. \ No Kev-9B JevBench result is published. These are Kev-8B (Qwen3). All JevBench numbers are on…
Read the full README ↗ · Preview checked 2026-11-12T18:05:42.424Z
Inside the original README — Document outline
- Jeeves – Reasoning improves Jev-like decision models
- Acknowledgements
- Highlights
- Problem
- Results
- Quickstart
- Python
- Options
- How it works
- Training
- Diffusion drafter
- Reproduce
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Jeeves – Reasoning improves Jev-like decision models
Repository facts
- Owner
- PostHog
- Primary language
- Python
- Stars
- 411
- Forks
- 21
- Open issues + pull requests
- 5
- License
- MIT
- Archived
- No
- Default branch
- master
- Created
- 2026-09-29T09:56:47.000Z
- Last push
- 2026-10-01T16:47:45.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-06T12:05:58.366Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer