» Tag
ai
22 postsHarness Engineering: Anatomy of 11 Production Coding Agents
A source-code audit of 11 coding agent harnesses reveals shared architecture, 29 design patterns, and the shift from tool to platform in 2026.
AWS Priming Method Converts Transformers into Hybrid SSMs Without Retraining
AWS's priming method reuses pretrained Transformer weights to cut hybrid state space model training costs by over 99%, with open-sourced models.
Tin: A GC-Free Systems Language Written Almost Entirely by AI Agents
Tin is a self-hosting, GC-free systems language built almost entirely by AI agents, featuring its own HTTP/2, gRPC and TLS 1.3 stack.
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.comWhat Stops Small Language Models from Driving a Database Agent
Explore the limitations of small language models in database agent tasks and their implications.
New Context Engineering Rules for Claude 5 Generation Models
Learn about context engineering and new application methods for Claude 5 models.
Microsoft ThinkingBox: Evaluating AI Agents by Their Outcomes
Microsoft ThinkingBox evaluates AI agents based on their outcomes, now accessible via Hugging Face.
Can Jev Model Be Trusted? Half a Million API Calls Say Not Always
The Jev model's reliability in automated decision-making is questioned. Test results provide crucial insights for engineers.
AI Agent Security: Six Controls from Nine Incidents
AI agents present three attack surfaces, and six controls can limit potential damage.
Poetry Becomes a New AI Security Threat as PoeLLM Malware Infects 3K+ Servers
The PoeLLM malware uses poetry to target AI systems, infecting over 3,000 servers. This highlights critical security risks.
call4me: A New Tool to Simplify Phone Calls
call4me is an innovative tool designed to simplify phone calls for users. It enables fast and effective communication.