The Stripe Experience You Deserve – Answer.AI
Welcome FastStripe to the Thunderdome| Answer.AI
Practical AI R&D| Answer.AI
Note TLDR: This post introduces fastmigrate, a Python database migration tool. It focuses on sqlite, and it does not require any particular ORM library. It’s suitable if you want to work directly with sqlite and keep things simple. For instructions, check out the fastmigrate repo. Let’s talk migrations! not the migrations we’re talking about Uh, no. Let’s talk about the database migration pattern. Migrations represent a powerful architectural pattern for managing change in your databa...| Answer.AI
Note from Jeremy: I’m thrilled that the legendary Daniel Roy Greenfeld took the time to dig into a very recent addition I made to fastcore: flexicache. It’s a super useful little tool which nowadays I use all the time. I hope you like it as much as Danny and I do! When coding in Python really like to use decorators to cache results from functions and methods, often to memory and sometimes to ephemeral stores like memcached. In fact, I’ve worked on and created several cache decorators, i...| Answer.AI
Introducing ReadBench, a straightforward way to see how well your favorite Vision-Language Models read text-rich images.| Answer.AI
My experience learning GPU programming, and implementing a new GPU education app in the process| Answer.AI
Welcome to this post! As a “TIL”, it’s a purposefully smaller blog post, containing just the key details. If you’d like to know more, head over to the technical report or play with the model on HuggingFace! TL;DR Traditionally (with some exceptions, of course), encoder models such as BERT are used with a task-specific head on top of the core encoder model. Functionally, this means that we discard all the language modelling goodness stored in the Masked Language Modelling head (the one...| Answer.AI
Accelerate your UI development with MonsterUI, our Python library for building frontend UIs quickly in FastHTML apps.| Answer.AI
Our impressions of Devin after giving it 20+ tasks.| Answer.AI
Finally, a Replacement for BERT Note This is a cross-post of the announcement blog post posted on the 🤗 HuggingFace blog. TL;DR This blog post introduces ModernBERT, a family of state-of-the-art encoder-only models representing improvements over older generation encoders across the board, with a 8192 sequence length, better downstream performance and much faster processing. ModernBERT is available as a slot-in replacement for any BERT-like models, with both a base (149M params) and large (...| Answer.AI
Transform your GitHub Jupyter notebooks into beautiful, readable web pages with a single URL change. No setup required.| Answer.AI
This is a quick note on a convenient way to use Nate Cooper’s ShellSage, one of the coolest pieces of tech to come out of AnswerAI recently. As Nate notes, ShellSage relies on tmux to do its magic. tmux is a terminal multiplexer. It traditionally sits in between your terminal emulator (like Terminal.app on macOS) and one or more shells (like bash). Sitting in between is what allows it to see your incoming commands, and their output, and make that context available to an AI. iTerm2 and tmux ...| Answer.AI
The Problem with Terminals We’ve all been there - staring at the terminal, trying to remember that obscure tar command or the right flags for ssh. Sure, you could Google it, but then you’re context-switching between documentation, Stack Overflow, and your terminal. Or maybe you’re using an AI assistant like ChatGPT or Claude, but now you’re copying and pasting between windows, losing your terminal context, and getting walls of text that don’t quite fit your specific situation. This ...| Answer.AI
What I’ve seen work and what doesn’t.| Answer.AI
fast.ai is joining Answer.AI, and we’re announcing a new kind of educational experience, ‘How To Solve It With Code’| Answer.AI
The art and science of crafting synthetic data for AI training| Answer.AI
This post was originally published here. Motivation: we often want to call LLMs in Starlette based apps (FastHTML, FastAPI, etc.) apps, and we don’t want to block the server on network calls to APIs. This post documents my explorations of various approaches that can run tasks in the background without blocking the main process. Tip You can see this notebook here. Using A SQL Database As A Queue We will use fastlite as the interface to our SQL database. Why You are often already using a data...| Answer.AI
TL;DR We’ve released (a while ago, now, with no further report of any major issues, warranting this blog post!) rerankers, a low-dependency Python library to provide a unified interface to all commonly used re-ranking models. It’s available on GitHub here. In this post, we quickly discuss: Why two-stage pipelines are so popular, and how they’re born of various trade-offs. The various methods now commonly used in re-ranking. rerankers itself, its design philosophy and how to use it. Intr...| Answer.AI
TL;DR WebGPU has arrived, opening a direct pipeline from the web browser to your local GPU. We’ve built WebGPU Puzzles to help you try it and explore the possibilities. It’s a simple, interactive way to learn GPU programming using nothing but your browser: gpupuzzles.answer.ai We challenge you to do the puzzles, then share your ideas about the possibilities with us! Introducing WebGPU Puzzles WebGPU Puzzles is a web incarnation of Sasha Rush’s GPU Puzzles - a series of small, fun, self-...| Answer.AI
We propose that those interested in providing LLM-friendly content add a /llms.txt file to their site. This is a markdown file that provides brief background information and guidance, along with links to markdown files providing more detailed information.| Answer.AI
A couple weeks ago, we released JaColBERTv2.5, using an updated ColBERT training recipe to create the state-of-the-art Japanese retrieval model. Today, we’re introducing a new model, answerai-colbert-small-v1 (🤗), a proof of concept for smaller, faster, modern ColBERT models. This new model builds upon the JaColBERTv2.5 recipe and has just 33 million parameters, meaning it’s able to search through hundreds of thousands of documents in milliseconds, on CPU. Despite its small size, it’...| Answer.AI
We recently sat down with Carson Gross, the creator of HTMX, to discuss how it’s changing the web.| Answer.AI
FastHTML is a new way to create modern interactive web apps. It scales down to a 6-line python file, and scales up to complex production apps.| Answer.AI
Introducing JaColBERTv2.5🇯🇵, the new best Japanese retrieval model. Through this release, we present a thorough analysis to better understand what helps in training a good multi-vector retrieval model.| Answer.AI
Practical AI R&D| Answer.AI
Are GPT-like models thinking? Unclear. But the Faith and Fate paper (Dziri, 2023) points out they are often “just” pattern matching.| Answer.AI
A historical analysis of what the earliest electrical and great applied R&D labs can teach Answer.AI, and potential pitfalls| Answer.AI
Answer.AI will figure out the fundamental research needed to tame AI, and the development path needed to make it useful in practice| Answer.AI
