Tootfinder

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Hao Peng, Yunjia Qi, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li
https://arxiv.org/abs/2506.09942 …

VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing large language models (LLMs), with verification engineering playing a central role. However, best practices for RL in instruction following remain underexplored. In this work, we explore the verification challenge in RL for instruction following and propose VerIF, a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model (e.g., QwQ-32B). …

🇺🇦 #NowPlaying on KEXP's #Audioasis
The Feelings:
🎵 Dearling Darling
#TheFeelings
https://thedarlingsuns.bandcamp.com/album/midnight-feelings
https://open.spotify.com/track/2l6J2SdGpsByRQ9L0fhAtf

There has been so much Saharan dust in the air that it’s odd for people to be talking about seeding.
Experts Reject Cloud Seeding Link to Central Texas Floods https://ground.news/article/controversy-erupts-over-weather-modification-following-texas-flooding_bc9a76

"The vast majority of arrests have been for failing to leave the area in defiance of requests from law enforcement, according to police."
The Latest: Los Angeles police have made nearly 400 arrests and detentions since Saturday - SooLeader
https://www.sooleader.com/michigan-news-ap/the-latest-los-angeles-police-have-made-nearly-400-arrests-and-detentions-since-saturday-10793135

The feeling when you find the root cause for a problem that has been bothering you for months. And it turns out to be fixable by adding a single letter. (To turn an "unsigned long" literal into an "unsigned long long" one.) (Actually I made it use the UINT64_C() macro from <cstdint>.)
Writing portable code is hard. And thanks, Windows, for keeping "long" as 32 bits even in 64-bit code.
Now, if only Clang or gcc on Linux would warn about such po…

Ex-Cowboys star released on bond following arrest conencted to fatal crash https://www.si.com/nfl/cowboys/news/ex-dallas-cowboys-star-released-bond-following-arrest-conencted-fatal-crash

"..some residents in #Ballymena have started to mark their front doors to indicate their nationality to avoid attack.."
I lived in this town, Ian Paisley's home town and DUP core territory, for 3 years as a teenager. Not been back.
It was characterised by narrow-mindedness and bigotry then in the 60s.
The last place to concentrate migrants, if that is what has happene…

Police injured, houses burned in second night of riots in Northern Ireland
Rioters said to target ‘foreigners’ in Northern Ireland town following alleged sexual assault of local teenage girl.

Was für eine – im negativen Sinn – raffinierte Werbung. Auf dem Plakat stand sinngemäß „Du liebst Bargeld – doch liebt das Bargeld dich zurück?“. Ich war empört, bin näher rangegangen, um zu sehen, wer hier wirbt.
Fehlanzeige. Es war nur dieser Spruch, sonst nichts. Schwarze Lettern auf weißem Untergrund.
Erst einen Monat später sehe ich, wer wohl dahintersteckt. Da wirbt nämlich P*yP*l in genau derselben Optik.

Defensive coordinator Shane Bowen wants takeaway-starved Giants filling treasure chest: 'Be a damn pirate' https://www.nfl.com/news/defensive-coordinator-shane-bowen-wants-takeaway-starved-giants-fi…

I go on Facebook
An Irishman in Ireland has posted a picture of his Irish flag flying outside his house (in response to some sports thing, apparently?)
The comments are exclusively full of Irish people spouting vitriol about the United States
...
The Anglosphere mind has been fully reverse-colonised by its biggest boi. They define themselves in opposition to it; without it, they would have no identity at all. Very sad state of affairs.