Tootfinder

The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Yuanxin Wang, Pawel Filipczuk, Anisha Garg, Amaan Dhada, Mohammad Hassanpour, David Bick, Ganesh Venkatesh
https://arxiv.org/abs/2509.19762

The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to wasted compute. We analyze this capability-cost trade-off and introduce an optimized reasoning workflow (\cepo) that empowers smaller open-source models to outperform models multiple times their size. We will open-source this workflow to enable further research. …

Kyler Murray has the 'ultimate confidence' in Trey Benson taking over for James Conner https://www.nfl.com/news/kyler-murray-has-the-ultimate-confidence-in-trey-benson-taking-over-for-james-conner

The Unwinnable Arms Race of AI Image Detection
Till Aczel, Lorenzo Vettor, Andreas Plesner, Roger Wattenhofer
https://arxiv.org/abs/2509.21135 https://arxi…

The Unwinnable Arms Race of AI Image Detection
The rapid progress of image generative AI has blurred the boundary between synthetic and real images, fueling an arms race between generators and discriminators. This paper investigates the conditions under which discriminators are most disadvantaged in this competition. We analyze two key factors: data dimensionality and data complexity. While increased dimensionality often strengthens the discriminators ability to detect subtle inconsistencies, complexity introduces a more nuanced effect. Usi…

The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
Zoe Kotti, Konstantina Dritsa, Diomidis Spinellis, Panos Louridas
https://arxiv.org/abs/2508.16131

The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
Code completion entails the task of providing missing tokens given a surrounding context. It can boost developer productivity while providing a powerful code discovery tool. Following the Large Language Model (LLM) wave, code completion has been approached with diverse LLMs fine-tuned on code (code LLMs). The performance of code LLMs can be assessed with downstream and intrinsic metrics. Downstream metrics are usually employed to evaluate the practical utility of a model, but can be unreliable …

Search for $\chi_{c1}\to \pi^{ }\pi^{-}\eta_c$ via $\psi(3686)\to\gamma\chi_{c1}$
BESIII Collaboration, et al.
https://arxiv.org/abs/2508.18601 https://arx…

Search for $χ_{c1}\to π^{+}π^{-}η_c$ via $ψ(3686)\toγχ_{c1}$
Utilizing $(2712.4 \pm 14.3) \times 10^6$ $ψ(3686)$ events collected with the BESIII detector at the BEPCII collider, we search for the hadronic transition process $χ_{c1} \to π^+π^-η_c$ following the decay $ψ(3686)\to γχ_{c1}$. No significant signal is observed, and an upper limit of $\mathcal{B}(χ_{c1}\toπ^+π^-η_c)$ is determined to be $3.1 times 10^{-4}$~at 90\% confidence level, which is one order of magnitude more stringent than the previous measurement.

Alaska Airlines stopped flying airplanes today because of an "IT outage". This is the second time in three months they stopped being an airline because of some computer problem. They've never been great but this kind of failure is unacceptable.

Jerry skeptical Dallas is '1 player away on defense' https://www.espn.com/nfl/story/_/id/46740452/cowboys-jerry-jones-willing-deal-trade-deadline-not-convinced-one-move-help-defense

Human resources software giant Workday has disclosed a data breach following a social engineering attack that compromised a third-party customer relationship management (CRM) platform.
https://www.computing.co.uk/news/2025/secu

Workday confirms data breach amid wave of Salesforce-linked cyberattacks
Human resources software giant Workday has disclosed a data breach following a social engineering attack that compromised a third-party customer relationship management (CRM) platform.

The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Yuanxin Wang, Pawel Filipczuk, Anisha Garg, Amaan Dhada, Mohammad Hassanpour, David Bick, Ganesh Venkatesh
https://arxiv.org/abs/2509.19762

The Conductor and the Engine: A Path Towards Co-Designed Reasoning
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to wasted compute. We analyze this capability-cost trade-off and introduce an optimized reasoning workflow (\cepo) that empowers smaller open-source models to outperform models multiple times their size. We will open-source this workflow to enable further research. …

Lions' unsung defense steps up, surprises even Dan Campbell: 'I had confidence, but nine points?' https://www.nfl.com/news/lions-unsung-defense-steps-up-surprises-even-dan-campbell-i-had-confidence-but-nine-points