Tootfinder

"I'm nimble like a cat."
Yeah, but like which cat?

StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
Xinkui Zhao, Yifan Zhang, Zhengyi Zhou, Yueshen Xu
https://arxiv.org/abs/2508.11665 https…

StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution
Recent advances in large language models (LLMs) have substantially enhanced automated code generation across a wide range of programming languages. Nonetheless, verifying the correctness and executability of LLM-generated code remains a significant challenge, as traditional methods rely on language-specific compilers and environment-dependent runtimes. To overcome these limitations, we introduce StackPilot, an LLM-native, multi-agent framework designed for language-agnostic code verification an…

#GiftLink 🔥
Jimmy Fallon Teases Trump’s U.K. Trip - The “Tonight Show” host said the royal couple are the president’s “second-favorite king and queen, next to Burger and Dairy.”
https://www.nytimes.com/2025/09/17/arts/television/jimmy-fallon-trump-royals.html?unlocked_article_code=1.m08.ttZ_.gdE82gqbdaS7&smid=url-share

Idea: rather than writing a bunch of stupid code to monitor your remote device, just pull some cheap fibre-optic cable from the remote end to your monitoring chair and duct-tape it to the status LEDs

A few weeks ago we decided the garden fence needed repainting. We bought a couple of big tins of wood stain paint and today I said "OK, I'll get that done this morning".
Have you ever over-estimated your abilities? I have.
It turns out that if you're not used to this sort of job, it takes about half an hour to paint a fence panel. And we have 14 of them in the garden.
Anyway, I've just finished the "quick morning job in the garden" now, at 6pm.
The fence looks bloody wonderful, though.
#DIY

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
Boyu Zhang, Ping He, Tianyu Du, Xuhong Zhang, Lei Yun, Kingsum Chow, Jianwei Yin
https://arxiv.org/abs/2509.13982

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting. This work presents CLMTracing, a black-box code LM watermarking framework employing the rul…

I guess we had a little bit of water come in through a loading dock door at work. It soaked a box full of Cat5 cable, not too bad. It's a good thing I moved a UPS off the floor where it was and onto a small rolling dolly a few months ago.
Also, USB-C is great because you can plug a cable into two different ports of a USB hub! Looks like it destroyed the cable and the hub. (Not sure who did it but people were trying to help while I was out.)
Anyway, all is up and running again…

Vamos a amenizar lo que queda de esta jornada de trabajo con la única, gran y querida Mon Laferte.
«La Trenza»
#MonLaferte #CD #NowPlaying #Musica

Trump and the Pentagon are considering creating a full-time
“Domestic Civil Disturbance Quick Reaction Force”
that could be called on to
quash civil unrest and protest at a moment’s notice,
according to internal documents reviewed by The Washington Post.
The force would be made up of about 600 National Guards troops,
half of which would be based on military bases in Alabama and Arizona,
ready at all times to fly into any given city or state to lay do…

Trump Plans Military “Reaction Force” to Use Against Americans
A disturbing new report reveals how Trump wants to use the military to crush civil unrest.

Towards Formal Verification of LLM-Generated Code from Natural Language Prompts
Aaron Councilman, David Fu, Aryan Gupta, Chengxiao Wang, David Grove, Yu-Xiong Wang, Vikram Adve
https://arxiv.org/abs/2507.13290

Towards Formal Verification of LLM-Generated Code from Natural Language Prompts
In the past few years LLMs have emerged as a tool that can aid programmers by taking natural language descriptions and generating code based on it. However, LLMs often generate incorrect code that users need to fix and the literature suggests users often struggle to detect these errors. In this work we seek to offer formal guarantees of correctness to LLM generated code; such guarantees could improve the experience of using AI Code Assistants and potentially enable natural language programming …