Hewett.cc

The biggest blocker to running local, safe, private, sustainable AI isn’t the configuration, it’s the hardware cost. The sheer potential of the technology has ballooned the cost of memory to several times what it was only a few years ago. Unless you’re a platinum level gamer with a NASA-level computer that has every memory slot filled, utilizing any real local AI model comes with serious constraints because odds are you simply don’t carry the firepower to run any model worth replacing just using free Claude, ChatGPT, Gemini, etc.

Continue reading 

It’s no secret right now that AI is everywhere, and it’s expensive. Trillions on trillions of dollars have been poured into the medium over the last decade. Providers recognize this, as one by one they all fall like dominoes transitioning into usage-based pricing models. This places additional pressure on the customer to make every single token count, as hundreds, if not thousands of dollars are at stake throughout AI-assisted project development.

Continue reading 