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
- Together AI | The AI Native Cloudtogether.ai
- Modal: High-performance AI infrastructuremodal.com
- Small Models Have Arrivedcalv.info
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- My picture of the present in AI — LessWronglesswrong.com
- Training Imperativesdan.io
- Can I run AI locally? | Hacker Newsnews.ycombinator.com
- AI Is Slowing Downwheresyoured.at
- A flat monthly subscription to open-source LLMs | Syntheticsynthetic.new
- AI Is Really Weirdwheresyoured.at
- There's An AI For That® — The front page of AItheresanaiforthat.com