←
Patrick4,058 posts
Patrick avatar

Patrick

@patrickmi

Currently, AI consulting. I have started, grown (to $100mm+) and sold successful startups. Love the outdoors.

◷ Joined July 2008▧ 515 Photos and videos
SpaceX avatar
⟳ Patrick retweeted
SpaceX@SpaceX·Nov 14

Mechazilla catches Starship! Congratulations to the entire SpaceX team on this incredible achievement!

1:33
Patrick avatar
Patrick@patrickmi·Nov 2

Some real news worth pondering. You’re welcome.

As of today Voyager 1 is one light-day from Earth - 25.9 billion km (16.1 billion miles) away. A radio signal now takes 24 hours to reach it. In ~50 years, it has traveled about 1/1500th of the way to Alpha Centauri, our nearest star at 4.27 light-years.

Post attachment
Patrick avatar
Patrick@patrickmi·12 Mar 2025

A beautiful morning along the White Clay Creek. First Eastern Phoebe and Wood Ducks of the year, too.

Post attachmentPost attachment
Patrick avatar
Patrick@patrickmi·3 Oct 2023

I like this - and agree with the position.

My interpretation of prompt engineering is this: 1. A LLM is a repository of many (millions) of vector programs mined from human-generated data, learned implicitly as a by-product of language compression. A "vector program" is just a very non-linear function that maps part of the latent space unto itself. 2. When you're prompting, you're fetching one of these programs and running it on an input -- part of your prompt serves as a kind of "program key" (as in database key) and part serves as program argument(s). Like, in "write this paragraph in the style of Shakespeare: {my paragraph}", the part "write this paragraph in the stye of X: Y" is a program key, with arguments X=Shakespeare and Y={my paragraph}. 3. The program fetched by your key may or may not work well for the task at hand. There's no reason why it should be optimal. There are lots of related programs to choose from. 4. Prompt engineering represents a search over many keys in order a find a program that is empirically more accurate for what you're trying to do. It's no different than trying different keywords when searching for a Python library. 5. Everything else is unnecessary anthropomorphism on the part of the prompter. You're not talking to a human who understands language the way you do. Stop pretending you are.

Cohere Labs avatar
⟳ Patrick retweeted
Cohere Labs@Cohere_Labs·21 Sep 2023

How portable are popular ML software frameworks? 🚚 Our recent cross-institutional collaboration reveals how costly straying from a narrow set of hardware-software combinations can be. 📜 arxiv.org/pdf/2309.07181.pdf

Post attachment
Patrick avatar
Patrick@patrickmi·25 Apr 2023

Kayaking on Snake Creek at Blue Springs State Park, Florida. The two biggest ‘gators were longer than our 14’ kayak. (Tri-colored Heron and White Ibis).

Post attachmentPost attachmentPost attachmentPost attachment
Patrick avatar
Patrick@patrickmi·3 Mar 2023

This week in Silicon Valley … several good runs, many good birds and quite a lot of robotics.

Post attachmentPost attachmentPost attachmentPost attachment