F1 Montreal Monday
I was visiting my family in Marin for Father’s Day, so couldn’t see the race till today. Thrilling to watch Alonso and Hamilton clash initially, but Alonso had pace in hand when it came down to it. Consistent with the season, Max had by far the most pace to spare.
Went for a bike ride after watching the race. Looped Calero Park from the South parking lot. I practiced carrying momentum and flow through the turns – keeping off the brakes while hitting the apex made a big difference. Strikingly unintuitive.
LLMs
On the drive back from LA I had plenty of time to think about using an LLM as an assistant on a larger project. There are two usability issues I currently see (more later as I’ll try some solutions this week):
- Limited context window / lack of memory
- Non-linear problem solving
The world is popping off on LLMs – here are some of the interesting links I came across.
- AI: First New UI Paradigm in 60 Years – A Nielsen Norman Group article positing “AI is introducing the third user-interface paradigm in computing history, shifting to a new interaction mechanism where users tell the computer what they want, not how to do it — thus reversing the locus of control.”
- The Secret Sauce behind 100K context window in LLMs: all tricks in one place – “techniques to speed up training and inference of LLMs to use large context window up to 100K input tokens during training and inference: ALiBi positional embedding, Sparse Attention, FlashAttention, Multi-Query attention, Conditional computation, and 80GB A100 GPUs.”
- OpenAI: Function calling and other API updates