Answer.AI - Practical AI R&D

Answer.AI is a new kind of AI R&D lab which creates practical end-user products based on foundational research breakthroughs. To learn more about the research agenda and background behind our work, see our launch post and an independent analysis of our lab. See below for a complete list of published articles.

Introducing fastmigrate

fastmigrate is a new, minimalist tool for data migrations in sqlite

Jun 13, 2025

Alexis Gallagher

Exploring flexicache

coding

open-source

tech

An exploration of using flexicache for caching in Python.

Jun 7, 2025

Daniel Roy Greenfeld

TIL: Vision-Language Models Read Worse (or Better) Than You Think

open-source

tech

research

Introducing ReadBench, a straightforward way to see how well your favorite Vision-Language Models read text-rich images.

Jun 5, 2025

Benjamin Clavié, Florian Brand

GPU Programming from Scratch

My experience learning GPU programming, and implementing a new GPU education app in the process

Mar 17, 2025

Sarah Pan

TIL: Masked Language Models Are Surprisingly Capable Zero-Shot Learners

open-source

tech

research

I have a [MASK] and I must classify: using masked language modeling for downstream tasks works surprisingly well.

Feb 10, 2025

Benjamin Clavié, Nathan Cooper, Benjamin Warner

MonsterUI: Bringing Beautiful UI to FastHTML

Accelerate your UI development with MonsterUI, our Python library for building frontend UIs quickly in FastHTML apps.

Feb 9, 2025

Isaac Flath, Jeremy Howard, & Audrey Roy Greenfeld

Thoughts On A Month With Devin

coding

Our impressions of Devin after giving it 20+ tasks.

Jan 8, 2025

Hamel Husain, Isaac Flath, Johno Whitaker

Finally, a Replacement for BERT: Introducing ModernBERT

open-source

tech

research

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.

Dec 19, 2024

Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Nathan Cooper, Griffin Adams, Johno Whitaker, Jeremy Howard, Iacopo Poli

nbsanity - Share Notebooks as Polished Web Pages in Seconds

Transform your GitHub Jupyter notebooks into beautiful, readable web pages with a single URL change. No setup required.

Dec 13, 2024

Hamel Husain

ShellSage Loves iTerm

tips

coding

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.

Dec 10, 2024

Alexis Gallagher

ShellSage - Your AI Bash Buddy

ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly

Dec 5, 2024

Nathan Cooper

Building an Audience Through Technical Writing: Strategies and Mistakes

writing

tips

What I’ve seen work and what doesn’t.

Nov 30, 2024

Hamel Husain

A New Chapter for fast.ai: How To Solve It With Code

education

open-source

tech

fast.ai is joining Answer.AI, and we’re announcing a new kind of educational experience, ‘How To Solve It With Code’

Nov 7, 2024

Jeremy Howard

How To T̶r̶a̶i̶n̶ Synthesize Your D̶r̶a̶g̶o̶n̶ Data

The art and science of crafting synthetic data for AI training

Oct 15, 2024

Nathan Cooper

Concurrency For Starlette Apps (e.g FastAPI / FastHTML)

Concurreny fundamentals for Python web apps

Oct 10, 2024

Hamel Husain

rerankers: A Lightweight Python Library to Unify Ranking Methods

open-source

tech

retrieval

Re-ranking is an integral component of many retrieval pipelines; however, there exist numerous approaches to it, all with different implementation methods. To mitigate this, we propose rerankers, a Python library which provides a simple, easy-to-use interface to all commonly used re-ranking approaches.

Sep 16, 2024

Benjamin Clavié

Learn GPU Programming in Your Browser

open-source

tech

coding

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…

Sep 13, 2024

Sarah Pan, Austin Huang

/llms.txt—a proposal to provide information to help LLMs use websites

webdev

open-source

tech

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.

Sep 3, 2024

Jeremy Howard

Small but Mighty: Introducing answerai-colbert-small

open-source

tech

retrieval

Say hello to answerai-colbert-small-v1, a tiny ColBERT model that punches well above its weight.

Aug 13, 2024

Benjamin Clavié

How HTMX is Revolutionizing Web Development — Interview with Carson Gross

webdev

interview

tech

We recently sat down with Carson Gross, the creator of HTMX, to discuss how it’s changing the web.

Aug 4, 2024

Elizabeth Creason

FastHTML: Modern web applications in pure Python

coding

webdev

open-source

tech

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.

Aug 3, 2024

Jeremy Howard

JaColBERTv2.5🇯🇵: Optimising Retrieval Training for Lower-Resources Languages

open-source

tech

retrieval

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.

Aug 2, 2024

Benjamin Clavié

Cold-Compress 1.0: A Hackable Toolkit for KV-Cache Compression

open-source

tech

Answer.AI is proud to publicly release Cold Compress 1.0, a toolkit for creating and benchmarking state-of-the-art KV cache compression methods. Built on top of GPT-Fast, it…

Aug 1, 2024

Griffin Adams, Faisal Ladhak

Faith and Fate: Transformers as fuzzy pattern matchers

research

Are GPT-like models thinking? Unclear. But the Faith and Fate paper (Dziri, 2023) points out they are often “just” pattern matching.

Jul 25, 2024

Alexis Gallagher

gpu.cpp: portable GPU compute for C++ with WebGPU

We’re thrilled to announce the release of gpu.cpp. gpu.cpp is a lightweight, open-source library that makes portable GPU compute with C++ simple.

Jul 13, 2024

Austin Huang

Politicians can’t change math

policy

It is not possible to provide assurance that a released model can’t be used to cause harm, because a released model can be changed.

Jun 28, 2024

Jeremy Howard

A little pooling goes a long way for multi-vector representations

open-source

tech

retrieval

We’re releasing an early version of a simple token pooling trick for ColBERT. This allows for considerable memory&disk footprint reduction with very minimal retrieval…

Jun 27, 2024

Benjamin Clavié

A new kind of literate program – Claudette

coding

open-source

tech

Claudette is the first ever ‘literate nbdev’ project. Its source is a rendered Notebook with callout notes and tips, HTML tables and images, detailed explanations. It explains how and why the code is written the way it is, along with how to use the libraries it depends on.

Jun 23, 2024

Jeremy Howard

Introducing Claudette, a new friend that makes Claude 3.5 Sonnet even nicer

Today, Anthropic launched the most powerful language model available: Claude 3.5 Sonnet. And today, we are making it ever better, with the launch of Claudette.

Jun 21, 2024

Jeremy Howard

The definition of ‘Artificial Intelligence’ in SB 1047 was actually meant for systems, not models

policy

SB 1047 defines “AI Model” using a definition designed for “AI Systems”, and as a result fails to cover anything.

Jun 19, 2024

Jeremy Howard

What policy makers need to know about AI (and what goes wrong if they don’t)

policy

Policy makers need to understand how AI really works. Otherwise bills like SB 1047 totally fail to achieve their stated goals.

Jun 17, 2024

Jeremy Howard

More=Better?

In this post I want to share a few quick experiments to show something that is both obvious and also perhaps underappreciated: you can get a sizeable quality boost from a…

May 17, 2024

Jonathan Whitaker

SB-1047 will stifle open-source AI and decrease safety

policy

By imposing the restrictions on open-source AI, SB-1047 could reduce AI safety, through reducing transparency, collaboration, diversity, and resilience.

Apr 29, 2024

Jeremy Howard