Llm

Wow, the new Mac Studios look really impressive. I can’t find the post that I saw last night about it, so I can’t share that author’s thoughts (I thought I commented or reacted at least, apparently not…), but what was interesting is the M3 Ultra goes up to 512GB of unified memory. 512GB… Of unified memory… If you’ve been playing with LLMs locally, and you have Apple Silicon, you’ll know that Apple’s unified memory is pretty performant, and it’s great for running local LLMs because the GPU uses the same system memory as the CPU, which means it can access most if not all of the RAM. ...

Introduction So very many years back when I was but a fledgling coder, armed with BASIC skills and deep into a Turbo Pascal with Objects book, I remember a conversation with my dad. Frustrated by the level of specificity needed to communicate with a machine, I asked, “Why has no-one made a programming language where I can just tell it ‘build this game for me’?” My dad, in his infinite wisdom, mused that cracking that puzzle – creating a natural language programming language – was a feat yet to be achieved. “Whoever manages to do that,” he predicted, “will make a fortune.” ...