Tech News
Extensible Software in the age of LLMs
The article discusses how LLMs excel at building 'Software for One'—personal apps tailored to individual workflows—while noting that existing pluggable software examples are mostly local tools with high barriers.
Conceptual integrity and counting lines of code
Last week I recorded an episode of the Talking Postgres podcast with Claire Giordano on the subject of "How AI is changing software development". We had a really great conversation.
Domain and publish date filters for Web Search on AgentCore
Web Search on Amazon Bedrock AgentCore now supports runtime domain and published-date filtering.
Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents
NVIDIA Holoscan is a platform for building real-time AI applications at the edge, from medical imaging to robotics. HoloHub is its companion repository.
How NVIDIA scales expertise with ChatGPT Work
NVIDIA teams use ChatGPT Work to reduce manual tasks, connect fast-moving signals, and scale successful workflows globally.
GitHub Repos
callstack/agent-device
Mobile app automation and verification for AI coding agents.
# TypeScript# adb# agentic aiMemPalace/mempalace
The best-benchmarked open-source AI memory system.
# Python# ai# chromadbmoazbuilds/CodeMachine-CLI
CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows.
# TypeScript# ai# automationResearch Papers
Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment
This paper surveys and tests various model compression techniques (like pruning and quantization) for running AI models on small devices, finding that no single method works best and that compression can sometimes hurt performance or even make models look better than they are.
ATLAS: Scaffold-Free Algorithm Synthesis by LLMs via Embedding-Guided Quality-Diversity Search
ATLAS is a new method that uses large language models and quality-diversity search to automatically design complete algorithms for combinatorial optimization problems without needing a predefined scaffold. It shows promising results on four NP-hard problems, producing diverse...
A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models
This paper explores whether Mixture-of-Experts (MoE) language models, which use specialized sub-networks for different tasks, develop language-specific routing when learning two languages. The authors find that a model trained on mixed English-German data shows stronger...