: Follow up: they are the same resolution (72 DPI)
: When asked to make an image lower res(olution), ChatGPT refuses because of built-in quality …
: This series of attempts to get Google’s Gemini model depict a horse riding an astronaut is …
: My colleague Mike Heavers made a nice overview of llamafile. llamafile allows you to run a #chatbot …
: My colleague Stephen Hood and MIECO fellow Justine Tunney released llamafile this week. …
: A lot of the reporting about Sam Altman’s return to OpenAI buries the fact that both of the …
: After writing a post on how LLMs answer math questions (tl;dr: answering math questions is not the …
: From Nadia Eghbal’s “Working in Public: the making and maintenance of open source …
: A colleague shared a project to run an LLM on iOS. The project sounds rad; the name is not (and …
: I decided to explore Replit’s AI coding feature and in the process made a thing: Do I need AI …
: Simon Wardley (part of the Mozilla Internet Ecosystem (MIECO) program) shared some thoughts on open …
: Notes on multimodal models, AI for infrastructure, fine tuning, and soft prompting I have been taking a lot of notes on readings and other sources, and am planning on posting them …
: [Field Report] Silicon Valley Generative AI Paper Reading Event: RWKV Preamble: learning about AI through events One of my approaches to learning about the industry, …
: More for less: OpenAI's larger and cheaper context window Yesterday (11/6/2023) OpenAI announced GPT-4 Turbo, an update to their state-of-the-art model GPT-4. …
: Casey Newton’s latest post about OpenAI’s agents (“GPTs”) is fascinating …
: Notes on Eric Jang's "How to Understand ML Papers Quickly" I found “How to Understand ML Papers Quickly” by Eric Jang (VP @ 1X, ex-Google) recently …
: Some reading from this week on AI Hacker News thread on difference between and rationale for using embeddings vs. fine-tuning an LLM. …
: The Mozilla AI Guide is now live! The AI Guide is an MVP resource we created for new and existing …
: Am I doing this right? Three factors that make learning with and about LLMs difficult When I started learning about large language models (LLMs), I hit wall almost immediately. I decided …
: TIL from this paper that although LLMs can translate text from one language to another, the cost of …
: I love getting sassed by ChatGPT (GPT-3.5) to just Google something with the attitude of “you …
: Catching up in “Hard Fork”: this segment on prompt engineering with Riley Goodside is …
: I am working on a bit of writing about the challenge of learning about LLMs by using them, and here …
: Oh, and one more: When using PAL chain the result translated the plus sign (+) into the word …
: Appendix to "Show Your Work" In the previous post I used a plan and execute agent to discuss the use of an LLM with an …
: Show your work: what to expect from how LLMs “do” math After finishing my undergrad in mathematics, I taught algebra and geometry to high schoolers. I …
: The generative AI paradox Note: After publishing this post, I have made some changes to my thinking. I will leave the below …
: Prompt: What happens at the end of the world? As part of some writing, I sent the prompt “What happens at the end of the world?” to …
: Here is a lesson in: 1/ the difference between less and few, and 2/ how much context matters to the …
: I feel seen in that attempting to log into LinkedIn whatsoever is suspicious. It’s me, …
: I am sort of surprised I haven’t read an explanation of hyperparameters for LLMs that uses …
: Getting Started but Going Where? What getting started guides tell us about the emerging shape of the generative AI domain Following the release of OpenAI’s ChatGPT, a tide of new educational resources washed in aimed at …
: TFW you think you know what you are doing after one tutorial
: Maybe just don’t take oil money AND use the term responsible.
: TWIL: Been reading about LLM context windows & came across this article: “We find that …
: Current personal reading: “On the Aesthetic Education of Man” by Friedrich Schiller …
: After reading through a bunch of LLM getting started tutorials and resources, here are a few …
: Y’all see this clip of Sam Altman inventing the Orb?
: TWIL (this week I learned) I recently got llama.cpp running on my desktop (tutorial forthcoming!) …