Tootfinder

DOGE’s work is done.
But where are its records?
The Department of Government Efficiency has quietly ended its formal mission,
leaving behind the most transformative restructuring of the federal government in a generation
— and little public accounting of its actions.
The “most transparent administration in history” is using a twofold strategy in an attempt to ensure no DOGE records ever see the light of day.

DOGE is formally done. Where are its records?
Plus: The State Department’s records shell game

OK, THIS is cool technology. Grain Weevil!
https://bsky.app/profile/did:plc:r643qxafn6b3pxfffiodojbn/post/3mlqfv53ogs2t

c0nc0rdance (@c0nc0rdance.bsky.social)
Chad Johnson is CEO of 'Grain Weevil'. His son did robotics competitions in high school, which inspired this little fella that breaks up hardened surfaces & levels grain to ensure it behaves like a liquid, avoids clumping. This probably saves 10-30 human lives a year. NO BOOTS IN THE GRAIN. [contains quote post or other embedded content]

Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments
Shuoming Zhang, Ruiyuan Xu, Haofeng Li, Qiuchu Yu, Yangyu Zhang, Chunwei Xia, Xiaobing Feng, Chenxi Wang, Huimin Cui, Jiacheng Zhao
https://arxiv.org/abs/2607.18357 https://arxiv.org/pdf/2607.18357 https://arxiv.org/html/2607.18357
arXiv:2607.18357v1 Announce Type: new
Abstract: Large language models now write a growing share of the world's code, increasingly inside agents and serving systems that compile, execute, or dispatch generated code without line-by-line review. This works well for mainstream languages but remains brittle for low-resource programming surfaces such as domain-specific languages, custom library APIs, and command-line tools. Even under grammar-constrained decoding, a model can still produce references invalid in the current environment: a buffer never declared, a column absent from the schema, a function the library does not provide, or an unsupported CLI option.
This paper introduces decode-time grammars: grammar fragments instantiated during generation from a runtime environment Gamma. A region-specific policy selects a fragment for each hole, and a tightening operator replaces open reference positions with Gamma-typed slots whose candidates are exactly the names, fields, APIs, or options available at that point. Newly generated declarations enter Gamma before later regions are decoded, so the constraining grammar can depend on the prefix already generated. This ensures not only grammatical correctness but also semantic correctness, by preventing references to undefined symbols.
We formalize grammar fragments as environment-indexed grammars ordered by refinement, prove No-Ghost soundness for Gamma-slotted fragments, show that refinement preserves this support-set guarantee, and characterize the boundary of mask-enforceable properties. We implement the approach in gproj with offline grammar induction and online policy resolution. Across TileLang, SQL, and P4, with models from 0.6B to 236B parameters, gproj eliminates ghost references by construction at moderate overhead over standard constrained decoding.
toXiv_bot_toot