Stories by simianwords

Use AI for reviewing code especially when the diff is huge

Ask HN: How are thinking efforts implemented?

MCP Needs an Approval Button

Why Deep Learning Works Even Though It Shouldn't

Investigating the hidden moat behind all the LLM apps

The state of AI voice assistants is bad but there's a clear winner

The generation vs. verification delta explains why LLM's are useful

Omni 1

AI can fix the fragmented online public transport space

A new wave of software efficiency is coming

Redesigning Agent Skills – two missing parts

Grok 4.3

The LLM costs are not going up

The LLM costs are not going up

Redesigning Agent Skills – two missing parts

Improving Agent Skills user experience by adding hooks

Under these conditions, LLM's basically never hallucinate

Why aren't LLM's trained on their own Chain Of Thought?

The generation vs. verification delta explains why LLM's are useful

Why domain specific LLMs won't exist: an intuition