Tootfinder

We are doomed: https://grith.ai/blog/clinejection-when-your-ai-tool-installs-another

A GitHub Issue Title Compromised 4,000 Developer Machines
A prompt injection in a GitHub issue triggered a chain reaction that ended with 4,000 developers getting OpenClaw installed without consent. The attack composes well-understood vulnerabilities into something new: one AI tool bootstrapping another.

Rethink Efficiency Side of Neural Combinatorial Solver: An Offline and Self-Play Paradigm
Zhenxing Xu, Zeyuan Ma, Weidong Bao, Hui Yan, Yan Zheng, Ji Wang
https://arxiv.org/abs/2602.20730 https://arxiv.org/pdf/2602.20730 https://arxiv.org/html/2602.20730
arXiv:2602.20730v1 Announce Type: new
Abstract: We propose ECO, a versatile learning paradigm that enables efficient offline self-play for Neural Combinatorial Optimization (NCO). ECO addresses key limitations in the field through: 1) Paradigm Shift: Moving beyond inefficient online paradigms, we introduce a two-phase offline paradigm consisting of supervised warm-up and iterative Direct Preference Optimization (DPO); 2) Architecture Shift: We deliberately design a Mamba-based architecture to further enhance the efficiency in the offline paradigm; and 3) Progressive Bootstrapping: To stabilize training, we employ a heuristic-based bootstrapping mechanism that ensures continuous policy improvement during training. Comparison results on TSP and CVRP highlight that ECO performs competitively with up-to-date baselines, with significant advantage on the efficiency side in terms of memory utilization and training throughput. We provide further in-depth analysis on the efficiency, throughput and memory usage of ECO. Ablation studies show rationale behind our designs.
toXiv_bot_toot