Tootfinder

On Entropy Control in LLM-RL Algorithms
Han Shen
https://arxiv.org/abs/2509.03493 https://arxiv.org/pdf/2509.03493

On Entropy Control in LLM-RL Algorithms
For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted in various popular RL algorithms including PPO, SAC and A3C. Although entropy regularization proves effective in robotic and games RL conventionally, studies found that it gives weak to no gains in LLM-RL training. In this work, we study the issues of entropy bonus in LLM-RL setting. Specifically, we first argue that …

Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation
Andrew G. A. Correa, Ana C. H de Matos
https://arxiv.org/abs/2509.00079 https://

Entropy-Guided Loop: Achieving Reasoning through Uncertainty-Aware Generation
Reasoning models often outperform smaller models but at 3--5$\times$ higher cost and added latency. We present entropy-guided refinement: a lightweight, test-time loop that uses token-level uncertainty to trigger a single, targeted refinement pass. We extract logprobs, compute Shannon entropy on top-$k$ alternatives, and apply a simple OR-logic trigger over perplexity, maximum token entropy, and low-confidence-token count. Unlike approaches that use entropy only for measurement or decoding, we …

Primal Scream en Chile
Fauna Primavera anunció un "opening Act" que estarš a cargo del grupo Primal Scream en el Teatro Coliseo el día 6 de noviembre. La venta de entradas ya estš disponible por puntoticket.
https://www.

Salesforce launches Agentforce Vibes, an enterprise vibe-coding tool and IDE featuring Vibe Codey, built on a fork from Cline's open source AI coding agent (Rebecca Szkutak/TechCrunch)
https://techcrunch.com/2025/10/01/salesforce-lau…

Salesforce launches enterprise vibe-coding product, Agentforce Vibes | TechCrunch
Salesforce is also releasing a vibe-coding agent named Vibe Codey to help companies foray into vibe coding with enterprise security.

"Weltgrößter illegaler Live-Sport-Streaming-Anbieter" angeblich stillgelegt
Der Entertainment-Verbund ACE hat nach eigener Aussage die Stilllegung einer großen illegalen Streaming-Seite erreicht. Der Verantwortliche widerspricht.

New paper published! ➡️ Climate change adaptation preferences of small enterprises
Vulnerable entrepreneurs’ preferences for climate risk management: A discrete choice experiment with micro-enterprises in the Philippines
Authors: #AnnKristin_Becker @…

Thermodynamics of Kerr black hole: Tsallis-Cirto composition law and entropy quantization
G. E. Volovik
https://arxiv.org/abs/2509.00748 https://arxiv.org/…

Thermodynamics of Kerr black hole: Tsallis-Cirto composition law and entropy quantization
The processes of splitting and merging of black holes obey the composition law generated by the Tsallis-Cirto $δ=2$ statistics. The same composition law expresses the full entropy of the Reissner-Nordström black hole via the entropies of its outer and inner horizons. He we apply this composition law to the entropy of the Kerr black hole. As distinct from Reissner-Nordström black hole, where the full entropy depends only on mass $M$ and does not depend on its charge $Q$, the entropy of Kerr b…

Crunchyroll blames a third-party vendor for AI-generated subtitles, with errors and references to ChatGPT, and says it is working to rectify the error (Igor Bonifacic/Engadget)
https://www.engadget.com/entertainment/str

Crunchyroll blames third-party vendor for AI subtitle mess
"We are investigating the matter and are working to rectify the error," Crunchyroll told Engadget.

Drohnenverdacht? Frankreich entert russischen Öltanker
Die französische Marine hat einen zur russischen Schattenflotte gehörenden Tanker aufgebracht. Das Schiff war während mysteriöser Drohnenflüge vor Dänemark.
http…

Q&A with Greg Gutfeld about Gutfeld! becoming the most-watched show in the 10pm ET slot, showing mainstream media "that they don't own the culture", more (Ali Lerman/Los Angeles Times)
https://www.latimes.com/entertainment-arts

Fox News' Greg Gutfeld makes late night his punch line: 'We're the ones now who are having fun'
The Fox News host explains what it's like to be a ratings leader in late-night TV.