Tech News
Codex starts encrypting sub-agent prompts
OpenAI's Codex now encrypts sub-agent prompts, hiding them from users, which affects local inspection tools and pushes users toward the responses API.
simonw/pedalican
Simon Willison accidentally discovered and created a custom animated pet for Codex Desktop, reminiscent of Clippy, that provides task updates.
Multi-agent social intelligence with Strands Agents and Amazon Bedrock
This post shows how Thrad.ai deployed a multi-agent system with Strands Agents and Amazon Bedrock AgentCore that automates the pipeline from prospect discovery through personalized email generation. The post compares.
How to Run an Autoresearch Workflow with RL Agent Skills and NVIDIA NeMo
Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect repositories, set up runtimes, resolve.
How to manage AI investments in the agentic era
Learn how enterprises can manage AI investments in the agentic era by measuring useful work per dollar, improving efficiency, and scaling high-value workflows.
GitHub Repos
hesreallyhim/awesome-claude-code
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at...
# Python# agent skills# agentic codeMemPalace/mempalace
The best-benchmarked open-source AI memory system.
# Python# ai# chromadbusewhale/Whale
Whale — blazingly fast, terminal-first AI coding agent for DeepSeek.
# Go# coding agent# deepseekResearch Papers
Do We Really Need Multimodal Emotion Language Models Larger Than 1B Parameters?
This paper shows that a small multimodal emotion recognition model (under 1B parameters) can match or outperform large 7B+ models by using knowledge distillation from a large teacher model, achieving better efficiency and competitive accuracy.
Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference
Jetson-PI enables real-time robot control on low-power devices by using a lightweight future correction module and confidence-based scheduling to overcome latency issues in asynchronous VLA inference.
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most agent systems run on desktops or servers, which support tool use and task automation.