Alessio’s Daily Thoughts

I have been playing with Hermes (a personal AI assistant) for the past week, and honestly, it has been amazing.

Legacy codebases are rough.

We keep asking AI models to do deterministic work, that is not ideal.

Lately I found myself naturally gravitating toward Claude Sonnet 5 with Medium reasoning.

I find it fascinating that we are throwing massive LLM models at every problem these days.

Remember that 10,000 hour rule from Outliers?

I think we are about to see a massive shift in how companies approach software, and SaaS vendors are going to feel the pain.

Teladoc and the pandemic made completely normal to discuss your health concerns over a video meeting.

An elegant solution for keeping OpenClaw from leaking credentials could be to put a proxy server between the bot and the outside world.

Until recently, startups had a genuine speed advantage.

LLMs have fundamentally shifted the calculus on whether to buy or build internal tools.

LLMs are incredible for writing code faster.

I have been thinking about how LLMs are trained on code, and honestly, the training data is probably a mess.