Hi friends, 2024 was a peaceful year of steady progress. With regard to my craft, the prototypes of 2023 were scaled and put into production, and I rediscovered the joy of building in public. On the personal side, I continued the prior year’s focus on health, further improving my diet and exercise habits, leading to measurable results. Past years: 2020, 2021, 2022, 2023 I appreciate you receiving this, but if you want to stop, simply unsubscribe. • • • 👉 Read in browser for best experience...
3 months ago • 4 min read
Hi friends, Recently, a dataset of 1M Bluesky posts unexpectedly sparked backlash from the Bluesky community. This incident uncovered strong anti-AI sentiment among Bluesky accounts, leaving the AI community feeling unwelcome on Bluesky. This write-up reflects on what happened, hypotheses on why it happened, and how the data/AI community responded. I appreciate you receiving this, but if you want to stop, simply unsubscribe. • • • 👉 Read in browser for best experience (web version has extras...
3 months ago • 5 min read
Hey friends, A very short email this week. I've been thinking a lot about writing lately and I've come to realize that there are a lot of rules, and at the same time no rules, about writing. I appreciate you receiving this, but if you want to stop, simply unsubscribe. • • • use simple words to be clear and concise use complex words to be sharp and precise write short sentences for the punch write long sentences to convey nuance spend 80% effort on an intro that hooks skip the intro, just get...
3 months ago • 1 min read
Hey friends, Over the past 18 months, the Latent Space Paper Club has had an unbroken streak of hosting paper club every single week. That’s at least 80 papers, and likely more, when we consider weeks where we cover related papers (e.g., LoRA + QLoRA). Together, we’ve pre-read and discuss a paper weekly, covering the fundamentals such as: Components: Attention, LayerNorm, FlashAttention, LoRA/QLoRA, ALiBi, RoPE Models: Transformer, BERT, T5, GPTs, Codex, LLaMAs, Mistral, CLIP, ViT, RWKV,...
3 months ago • 5 min read
Hey friends, I just upgraded my personal laptop from a 2019 Intel MacBook Pro to an M4 MacBook Pro. Like all my new devices, instead of restoring from a backup, I try to Marie Kondo my digital life and start from a clean slate. This also lets me reexamine my existing tools and explore new options. Here’s my minimal Mac setup guide if you want to follow along. MacOS settings Basic developer tools Research, writing, development Productivity and quality of life Entertainment and communications...
4 months ago • 3 min read
Hey friends, I'm in a reflective mood in the last two months of 2024 and revisited + compiled my notes from conferences this year. Here are 39 lessons I took away, each written to be focused around machine learning, production & scaling, execution & collaboration, building for customers, and speaking at conferences. I hope you find them useful. P.S., My friend Hamel is back with a free email course on AI for executives. He was the one who organized an LLM course (with Dan) that became an epic...
4 months ago • 8 min read
Hey friends, I've been thinking a lot about evals. Out of all the patterns for building LLM systems and products, it's been the hardest to scale. Thus, I built AlignEval tht makes building LLM-evaluators as simple as four simple steps: Upload a CSV file with columns for input and output Look at the data and label samples as pass or fail Define eval criteria, run the LLM-evaluator, check results Optimize the LLM-evaluator with dev-test splits Give it a try at aligneval.com, read the writeup...
4 months ago • 9 min read
Hey friends, Recently, I've been wondering if I should migrate from my current web app stack (FastAPI, HTML, CSS, and some JavaScript) towards a modern web framework. I was particularly interested in FastHTML, Next.js, and Svelte. To learn more about these frameworks, I built the same web app using each of them. Here's what I learned, plus some thoughts on how coding assistances can and will influence developer habits and choices. I appreciate you receiving this, but if you want to stop,...
6 months ago • 6 min read
Hey friends, I've been thinking and experimenting a lot with how to apply, evaluate, and operate LLM-evaluators and have gone down the rabbit hole on papers and results. Here's a writeup on what I've learned, as well as my intuition on it. It's a very long piece (49 min read) and so I'm only sending you the intro section. It'll be easier to read the full thing on my site. I appreciate you receiving this, but if you want to stop, simply unsubscribe. 👉 Read in browser for best experience (web...
7 months ago • 4 min read
