AI Coding at Home Without Going Broke | Stephen Bochinski
There are three ways to do AI coding at home without spending like a company, and which one fits depends mostly on how much you trust the next year of hardwa...
There are three ways to do AI coding at home without spending like a company, and which one fits depends mostly on how much you trust the next year of hardware and model releases. The first is to self host. You buy the machine, run open source models locally, and pay nothing per token after that. The upfront cost is steep and the models you can actually run at home are weaker than what the frontier labs ship, so this only pays off if you can keep the rig busy with long running tasks where a slower, cheaper model grinds away overnight. Most people can’t keep a home machine that loaded, and…
saved by
related reading
- ICONIQ | AI Economics is a Design Problemiconiq.com
- How much I'm paying for AI productivity software (and the future of AI use)jacquesthibodeau.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Training Imperativesdan.io
- When Should You Move to Cheaper Models?artificialinvestment.substack.com
- How much does it cost to train frontier AI models? | Epoch AIepoch.ai
- Building Auto Mode for Open Models — Benjamin Andersonbenanderson.work
- Navigating the High Cost of AI Compute | Andreessen Horowitza16z.com
- Why compute might get 10x more expensive in coming yearsdwarkesh.com
- Don’t Outsource Your Thinkingteltam.github.io
- AI Is Slowing Downwheresyoured.at
- Can I run AI locally? | Hacker Newsnews.ycombinator.com