Tech News
Ask HN: How do you manage skills files?
Developers on Hacker News debate the utility of AI agent 'skills' files, with some dismissing them as snake oil while others advocate for maintaining personal, version-controlled skill sets.
Quoting Jakub Pachocki
The strongest argument I see for continuing to train much smarter models quickly is the need to build defensive systems against the dangers posed by other AI.
modelcontextprotocol/python-sdk v2.2.0
pip install -U mcp. Docs: A few defaults changed in this release.
Replaceable but Employed: Automation and the Meaning of Work
A discussion on automation's impact on labor value and bargaining power, referencing a paper that models how automation can reduce work's worth before eliminating jobs.
216M Spy TVs – The LG Smart TV Problem [video]
A video highlights that LG smart TVs, with 216 million units sold, are logging user data under broad consent terms, prompting developers to discuss privacy risks and practical countermeasures like disabling network...
GitHub Repos
HKUDS/nanobot
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
# Python# agent framework# ai agentcalesthio/OpenMontage
World's first open-source, agentic video production system.
# Python# agent# agentic aivercel/workflow
Workflow SDK: Build durable, reliable, and observable apps and AI Agents in TypeScript
# TypeScript# ai agents# durable executionResearch Papers
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
RoboSPA is a new benchmark and dataset for testing vision-language-action (VLA) robots on tasks with increasing spatial and procedural difficulty, showing that current models still struggle with complex reasoning and long-horizon planning.
Towards AI-Driven Nanomedicine Discovery: A Benchmark and Multimodal Learning Framework for Nano Self-Assembly Prediction
This paper creates a public benchmark (NSA-Bench) for predicting whether pairs of molecules will self-assemble into nanoparticles, and proposes a multimodal neural network (NSA-Net) that combines molecular graphs, sequences, and physicochemical properties to make these...
No-Regret Bayesian Optimization with Finite-Library Input-Warped Kernels
Finite-Library Input-Warped Bayesian Optimization (FLIWBO), which selects warps from a finite library of smooth input maps by any history-dependent rule, and adapts the input geometry to accelerate learning while retaining high-probability convergence guarantees under mild...