answerdotai's profile picture. A new kind of AI R&D lab which creates practical end-user products based on foundational research breakthroughs

Answer.AI

@answerdotai

A new kind of AI R&D lab which creates practical end-user products based on foundational research breakthroughs

Answer.AI reposted

Most AI tools give the illusion of rapid progress but results that don't surive first contact with testing. The @answerdotai team have done an incredible job designing solveit in a way that makes it genuinely hard to fall into the traps and dead ends of most "vibe coding" tools.


Answer.AI reposted

It's a strange time to be a programmer—easier than ever to get started, but easier to let AI steer you into frustration. We've got an antidote that we've been using ourselves with 1000 preview users for the last year: "solveit" Now you can join us.🧵 answer.ai/posts/2025-10-…


Answer.AI reposted

18 months ago, @karpathy set a challenge: "Can you take my 2h13m tokenizer video and translate [into] a book chapter". We've done it! It includes prose, code & key images. It's a great way to learn this key piece of how LLMs work. fast.ai/posts/2025-10-…


Answer.AI reposted

99% of AI "guidance" online is of the (fantasy) genre "10x your productivity by running parallel Claude Codes that orchestrate sub-Claude-Codes that dynamically spin up sub-sub-Claude-Codes". @jeremyphoward's solveit is the opposite and I can't recommend his course highly enough.

It's a strange time to be a programmer—easier than ever to get started, but easier to let AI steer you into frustration. We've got an antidote that we've been using ourselves with 1000 preview users for the last year: "solveit" Now you can join us.🧵 answer.ai/posts/2025-10-…



Answer.AI reposted

The SolveIt course by @answerdotai is open to signups again! Doing the course in March has had a huge impact on how I build projects and code with LLMs. I love it so much I'm joining again to learn new workflows and tricks. You will (most likely) not regret signing up!

It's a strange time to be a programmer—easier than ever to get started, but easier to let AI steer you into frustration. We've got an antidote that we've been using ourselves with 1000 preview users for the last year: "solveit" Now you can join us.🧵 answer.ai/posts/2025-10-…



Exciting news - the new solveit course is now open for signups! Details below👇👇👇

It's a strange time to be a programmer—easier than ever to get started, but easier to let AI steer you into frustration. We've got an antidote that we've been using ourselves with 1000 preview users for the last year: "solveit" Now you can join us.🧵 answer.ai/posts/2025-10-…



Answer.AI reposted

Here is my workflow for doing Machine Learning on remote machines. It features: • execnb, a little-known gem by @answerdotai • tips on using Jupyter Notebook in @code • a workflow based on @LambdaAPI • thoughts on how computing needs of ML practitioners have evolved Link…

radekosmulski's tweet image. Here is my workflow for doing Machine Learning on remote machines.

It features:

• execnb, a little-known gem by @answerdotai 
• tips on using Jupyter Notebook in @code
• a workflow based on @LambdaAPI 
• thoughts on how computing needs of ML practitioners have evolved

Link…

Answer.AI reposted

Embrace being a crud monkey

You've been tricked! Very high traffic is cheap too, I serve 314,000,000 requests per month One VPS can be just $50/mo to handle all this traffic, with Cloudflare caching most of it (for free!)

levelsio's tweet image. You've been tricked!

Very high traffic is cheap too, I serve 314,000,000 requests per month

One VPS can be just $50/mo to handle all this traffic, with Cloudflare caching most of it (for free!)


Answer.AI reposted

I took the Solveit course by @jeremyphoward and @johnowhitaker. Main insight: we can't expect one-shot AI solutions because we can't even ask the right question on the first try. It's no wonder most AI tools feel like a self-driving car hell-bent on driving off a cliff. 🧵

R_Dimm's tweet image. I took the Solveit course by @jeremyphoward and @johnowhitaker.

Main insight: we can't expect one-shot AI solutions because we can't even ask the right question on the first try.

It's no wonder most AI tools feel like a self-driving car hell-bent on driving off a cliff. 🧵

Answer.AI reposted

At @answerdotai we built SolveIt to improve how we develop software - including SolveIt itself 🔄 Here I'm using it to learn our own fastcore library, with immediate code execution right in the dialog. gist.github.com/erikgaas/11a24…


Answer.AI reposted

Building this quiz app in FastHTML (from @answerdotai) to test out some Claude Code workflows. Let me know what features you'd like to see added in the next round of updates, and I'll see what I can do! 🙂


Answer.AI reposted

Claudette (a lib for interacting with Claude from Python) is such a true gem 🥰 You not only get a super streamlined way of calling out to Claude from your code, but you also learn about all the things Claude can do. Chat is only a start. Some tips on how to learn it:


Answer.AI reposted

For over a year, @jeremyphoward has been in stealth mode. In this exclusive talk, he showcases what he's been working on. He & @johnowhitaker show us SolveIt, a new dev environment and programming paradigm. 🤯 Imagine this workflow: - Build a web app & interact with its UI…


Answer.AI reposted

Introducing irouter, a super simple interface to access 100s of (@OpenRouterAI) LLMs with 2 lines of code. It supports multi-modal inputs (text, images, PDF, audio) and tool loops. Mix and match as you see fit. pip install irouter github.com/CarloLepelaars… Examples (1/6) 👇

carlolepelaars's tweet image. Introducing irouter, a super simple interface to access 100s of (@OpenRouterAI) LLMs with 2 lines of code.

It supports multi-modal inputs (text, images, PDF, audio) and tool loops. Mix and match as you see fit.

pip install irouter
github.com/CarloLepelaars…

Examples (1/6) 👇

Answer.AI reposted

Thanks to our new faststripe lib, it's now this easy to integrate @stripe into your python app:

jeremyphoward's tweet image. Thanks to our new faststripe lib, it's now this easy to integrate @stripe into your python app:

At @answerdotai, we integrate @stripe into lots of projects. Every time, I found myself doing the same dance: create product, create price, create checkout session. Then hunting docs for parameters for each. So we built FastStripe, a self-documenting Stripe SDK that's easy to…

ncooper57's tweet image. At @answerdotai, we integrate @stripe into lots of projects. Every time, I found myself doing the same dance: create product, create price, create checkout session. Then hunting docs for parameters for each. So we built FastStripe, a self-documenting Stripe SDK that's easy to…
ncooper57's tweet image. At @answerdotai, we integrate @stripe into lots of projects. Every time, I found myself doing the same dance: create product, create price, create checkout session. Then hunting docs for parameters for each. So we built FastStripe, a self-documenting Stripe SDK that's easy to…


Answer.AI reposted

Happy to share our ModernBERT encoder trained on 1.2 trillion Scandinavian tokens based of answerdotai/ModernBERT-large @AISweden @answerdotai @LightOnIO @LUMIhpc huggingface.co/AI-Sweden-Mode…


Answer.AI reposted

Our Startup and AI legal expert @LukeVerswey is doing a special lesson with @jxnlco -- highly recommended for all founders or anyone considering starting a company. maven.com/p/895e37/legal…


Answer.AI reposted

Now Agentic Coding is here, how will orgs and teams adapt to this Brave New World! In part 2 of my series, I cover @emollick's Leadership → Crowd → Lab model and look at real examples of what @Shopify, @answerdotai, @cursor_ai, and even Google are doing about it. Learn why…

madhavajay's tweet image. Now Agentic Coding is here, how will orgs and teams adapt to this Brave New World!

In part 2 of my series, I cover @emollick's Leadership → Crowd → Lab model and look at real examples of what @Shopify, @answerdotai, @cursor_ai, and even Google are doing about it.

Learn why…

Answer.AI reposted

"We're gonna need a bigger graph"

Post credits easter egg: Hey did you wonder what if we trained a bigger model? Where would that take us? Yeah, us too. So we're gonna train a "huge" version of this model in 2025. We might need to change the y-axis on this graph…

jeremyphoward's tweet image. Post credits easter egg:

Hey did you wonder what if we trained a bigger model? Where would that take us?

Yeah, us too.

So we're gonna train a "huge" version of this model in 2025. We might need to change the y-axis on this graph…


United States Trends

Loading...

Something went wrong.


Something went wrong.