Ditch ChatGPT: Run A Fast LLM On Your Computer Instead
HackernoonMay 17, 20248 min
Run language models on your machine for faster, private work without sending prompts to the cloud.
Read essay →
Systems for places people love.
A café must be discoverable.
A plumbing company must answer when customers call.
A team under pressure must make sense of information quickly.
The work sits behind those moments, making systems easier to find, understand, and act through.
Helping a neighborhood café become easier to discover and return to.
Helping service businesses capture opportunities they would otherwise miss.
Helping operators make sense of information under uncertainty.
Helping families find a home with legible search and calm presentation.
Run language models on your machine for faster, private work without sending prompts to the cloud.
Read essay →
OS virtualization, Docker, Kubernetes, and monitoring containers in production.
Read essay →