September 8, 2026 · AI
Can tgrep, CodeGraph, Mantic, or ripwire Replace ripgrep?
Four code search tools measured against ripgrep on eight repos
#Code Search
#ripgrep
#tgrep
#CodeGraph
AI
All Posts
한국어September 7, 2026 · AI
ego-browser and Aside Fail Differently
Two browser agents on the same missions: structure and defects
#AI
#Agent
#Browser Automation
#Playwright
AI
July 2, 2026 · AI
Driving a Free Colab GPU from the CLI
Use google-colab-cli to drive free Colab GPUs from your laptop
#Colab
#google-colab-cli
#GPU
#vLLM
AI
July 2, 2026 · AI
Wiring codex to a Local Qwen — ollama, vLLM, and the developer role
Point OpenAI codex CLI at a local Qwen or gemma in five minutes
#codex
#LLM
#vLLM
#ollama
AI
June 25, 2026 · AI
Speeding up LLM inference with MTP and diffusion
MTP and diffusion inference on Gemma 4 and Qwen 3.6, fp8 on one H100
#LLM
#vLLM
#MTP
#Speculative Decoding
AI
May 27, 2026 · AI
Requirements as Latent State
Why spec-driven development is a requirements-inference architecture
#AI
#Agent
#Requirements
#Spec-Driven
AI
May 27, 2026 · AI
Skill and Harness
Why skills and harnesses overlap in implementation
#AI
#Agent
#Harness
#Skills
AI
May 26, 2026 · AI
Harness as Environment
How harness design determines whether agents actually adapt.
#AI
#Agent
#Harness
#Memory
AI
May 22, 2026 · AI
Memory as Adaptation
Why agent memory moved from RAG storage to the foundation of policy adaptation
#AI
#Agent
#Memory
#RAG
May 22, 2026 · AI
Weights, Prompts, Codes as Parameters
Weights, prompts, and code as parameters at different layers of a learnable policy space
#AI
#Agent
#LLM
#POMDP
