Tootfinder

I tried to convince #Claude Code #ai to write a #docker sandbox to run it in. Here are the results.

GitHub - cwensel/claude-sandbox: A docker sandbox for running Claude Code
A docker sandbox for running Claude Code. Contribute to cwensel/claude-sandbox development by creating an account on GitHub.

This https://arxiv.org/abs/2505.19253 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
Deep research systems represent an emerging class of agentic information retrieval methods that generate comprehensive and well-supported reports to complex queries. However, most existing frameworks rely on dynamic commercial search APIs, which pose reproducibility and transparency challenges in addition to their cost. To address these limitations, we introduce DeepResearchGym, an open-source sandbox that combines a reproducible search API with a rigorous evaluation protocol for benchmarking d…

This https://arxiv.org/abs/2505.23387 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to address this, employing a closed-loop system where LLMs iteratively refine code based on empirical performance feedback from an execution sandbox. We explore three training strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and G…

TL;DR Amazon's SES in sandbox mode only sends to validated addresses and identities defined in the configuration.
https://winkelwagen.de/2025/05/29/aws-ses-message-rejected-email-address-is-not-verified/

AWS SES Message rejected: Email address is not verified.
I configured one of our Magento 2 stage instances today to use Amazon SES to send emails instead of dumping them into mailhog. But I got the following error: Message rejected: Email address is not …

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
Mingzhe Du, Luu Tuan Tuan, Yue Liu, Yuhao Qing, Dong Huang, Xinyi He, Qian Liu, Zejun Ma, See-kiong Ng
https://arxiv.org/abs/2505.23387

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to address this, employing a closed-loop system where LLMs iteratively refine code based on empirical performance feedback from an execution sandbox. We explore three training strategies: Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and G…