Thread Truncated (Cap Enforced)
Only the first 20 tweets are unrolled into slides to ensure reliable PDF exporting and high server performance.
Canvas & Ratio
Choose your destination platform format
Layout Template
Choose a content structure for your slides
Preset Themes
Typography & Sizing
Brand Kit Customization
AGENCYConfigure brand assets for headers & footers
Outro Slide CTA
Customize your closing call-to-action slide
Background Pattern
Build Your Carousel
Drag and drop any post card below onto a slide, or use the quick buttons to insert content/images instantly!
You don't need billions to train the next ChatGPT All you need is a $100 and Andrej's Karpathy's Nanochat I used it for the last week here is what I found
---
<i>Disclaimer: the cost of compute is expected to go down the next decade. Even though my statement is hyperbolic , you can get a usable version in less than $100. This is a build and not a bold statement</i>. I do agree that the capex right now to train these AI models is insanely high, but I'm expecting that one day will come a time where we will be able to train awesome frontier models at really economical prices.
---
I spent ~$100 and one weekend training a ChatGPT-style model <b>from scratch</b> on my own notes, writing, and exported AI chats. It now answers in my voice and recalls my own ideas, with no API and no rented brain.
This guide is the version I wish I'd had: every command, every code change, and <b>plain-English explanations of the jargon</b> so you don't get stuck.
If you've never trained a model before, you're the target reader. Take it one step at a time.
## Read this first (what you're signing up for)
<b>What you'll end up with:</b> a small GPT, roughly as capable as OpenAI's original GPT-2 (2019), fine-tuned on your own data so it sounds like you and knows your stuff. You can chat with it in a ChatGPT-style web page.
<b>Honest expectations:</b> this is not GPT-4. It's "a kindergartener with your memories", charming, useful for recall and drafting, and confidently wrong sometimes. The magic isn't raw IQ; it's that it's <i>yours</i>, it's private, and you understand every part of it.
<b>What it costs:</b> about <b>$48–$100</b> in rented GPU time for the full run. You can learn the entire pipeline for <b>~$0</b> first (more on that below).
<b>Skills you need:</b>
• Comfort typing commands into a terminal (copy-paste is fine).
• Basic Python literacy helps for the data step, but I'll give you working scripts.
• <b>No machine-learning background required.</b> I'll explain the concepts as we go.
<b>Time:</b> budget a weekend. The actual training is ~3 hours; the rest is setup and preparing your data.
## The 60-second mental model
Training a chatbot happens in <b>two big phases</b>. Keep these straight and everything else makes sense.
1. <b>Pretraining</b> → produces the <i>base model</i>. The model reads a huge pile of internet text and learns one skill: predict the next word. This is where it learns grammar, facts, and reasoning. It's expensive (this is the ~3 hours of GPU time). The result talks like the internet, it can <i>complete</i> text but can't <i>chat</i>.
1. <b>Fine-tuning (SFT)</b> → produces the <i>chat model</i>. You show the base model thousands of example conversations so it learns to answer like an assistant. This is cheap and fast (minutes). <b>This is where your personal data goes in.</b>