LLMs
Why LLMs Aren't the Next Generation of Compilers
2/7/2026
LLMs
Rethinking Transformer Efficiency: FORTH-Style Postfix Outperforms Prefix in LLM Benchmarks
2/7/2026

LLMs
Datadog Integrates Google Agent Development Kit into LLM Observability Tools
2/6/2026

LLMs
Context Engineering for Coding Agents
2/5/2026

LLMs
Fragments: February 4 - AI, Code, and the State of Minnesota
2/4/2026
LLMs
The Hidden Quadratic: How LLM Agent Cache Reads Are Eating Your Budget
2/3/2026

LLMs
Inside Nano-vLLM: How Modern Inference Engines Transform Prompts into Tokens
2/2/2026

LLMs
AutoBe's Hardcore Function Calling Benchmark Pushes LLM Backend Generation to New Limits
2/2/2026

LLMs
LLMs as Emacs Elisp Assistants: Reducing the Friction of Infinite Customization
2/2/2026

LLMs
Arcee AI launches Trinity Large, a 400B-parameter open-weight model challenging Meta's Llama 4 Maverick
1/29/2026

LLMs
GNU gettext Reaches Version 1.0 After 30+ Years In Development - Adds LLM Features
1/29/2026
LLMs
The Double-Edged Sword of AI-Assisted Code Porting: Lessons from Translating TinyEMU to Go
1/28/2026

LLMs
Turns out I was wrong about TDD
1/25/2026