corpus.blog
43,317 blogs · 5,519,570 posts Claim your blog
Record · corpus.blog/posts/01a0d80c-096c-722f-87b5-b981eb56f966

Reinforcement Learning for Calibrated Decisions (RLCD)

dSebastien · published 23 September 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at dsebastien.net Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
13
Words captured
1,453

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
Typesafe AI: System One Models and Jev
typesafe.ai
https://docs.typesafe.ai/introduction/machine-learning-primer?ref=dsebastien.net
docs.typesafe.ai
https://docs.typesafe.ai/model-jaggedness/jev-1.13?ref=dsebastien.net
docs.typesafe.ai
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
latent.space
https://archerhume.com/posts/jevs-architecture-unmasked/?ref=dsebastien.net
archerhume.com
https://www.beri.net/article/typesafe-jev-typed-decision-model-calibration-decomposition-shadow-eval?ref=dsebastien.net
beri.net
https://anthonymaio.substack.com/p/jev-the-language-model-that-wont
anthonymaio.substack.com
https://di-zhang-llm.github.io/blog/what-is-rlcd-the-secret-behind-jev/?ref=dsebastien.net
di-zhang-llm.github.io
https://www.turingpost.com/p/what-is-jev-rlcd?ref=dsebastien.net
turingpost.com
https://arxiv.org/abs/2507.16806?ref=dsebastien.net
arxiv.org
https://arxiv.org/abs/2503.02623?ref=dsebastien.net
arxiv.org
https://arxiv.org/abs/2207.05221?ref=dsebastien.net
arxiv.org
https://arxiv.org/abs/2410.09724?ref=dsebastien.net
arxiv.org
Elsewhere on dsebastien.net (19)
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Reinforcement+Learning+for+Calibrated+Decisions+(RLCD
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/TypeSafe+AI?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Jev?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/AI+Post-Training?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Reinforcement+Learning+From+Human+Feedback+(RLHF
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Reinforcement+Learning+with+Verifiable+Rewards+(RLVR
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Synthetic+Data?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Jagged+Intelligence?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Proper+Scoring+Rules?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/GPT-6+Astra?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Claude+Fable+5.1?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/OpenAI?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Anthropic?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/AI+Model+Calibration?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Confidence-Gated+Routing?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/36+People/Diogo+Almeida?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Mode+Collapse?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/System+One+Models?ref=dsebastien.net
notes.dsebastien.net
https://notes.dsebastien.net/30+Areas/33+Permanent+notes/33.02+Content/Decision+Models+(DMs
notes.dsebastien.net