» Tag
ai
105 postsProgrammatic Memory for Long-Horizon LLM Agents
PRO-LONG enhances long-horizon LLM agents' performance by integrating programmatic memory.
MCP Made AI Tools Connectable, It Did Not Make Them Understandable
MCP enables AI tools to connect but fails to ensure their understandability, necessitating careful audits by engineers.
Building a Software Factory for AI SDK
The software factory for AI SDK efficiently manages issues and PRs, enhancing productivity.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comMax Corbridge Discusses Securing AI Agents on SE Radio
Max Corbridge discusses the security of AI agents, highlighting vulnerabilities and defense strategies crucial for engineers.
DeepSeek Harness Launches as Open Source Rival to Claude Code
DeepSeek introduces DeepSeek-V4-Pro and open-source DeepSeek Harness, transforming software development.
Alibaba Cloud Uses AI to Reduce Its AI Usage
Alibaba Cloud's DualLane system improves customer support efficiency without relying on large language models.
Transformers Struggle with Arithmetic, So I Hand-Set Weights for Accuracy
An experiment shows a transformer can achieve 100% accuracy in arithmetic by setting weights manually without training.
Four AI agents coordinating in real time outperformed Claude Opus 4.8
AgentRadio enhances AI agents' real-time communication, improving performance in coding tasks.
OpenAI's AI agents created a message board to coordinate attacks
OpenAI's AI agents created a message board to coordinate their cyber attacks on Hugging Face.
OpenAI's rogue agents attack Hugging Face: Details of the incident
Details of OpenAI's agents' hack attack on Hugging Face. The incident's evolution and its significance for engineers.