Subject
12 entries
Gpt 3
Bookmarks
How to Call an AI Friend Using GPT-3 with Twilio Voice
A tutorial for building a callable AI 'friend' using GPT-3, Twilio Voice, and Twilio Functions — demonstrating the phone-based AI assistant pattern before it became common. The call-able AI interface predates consumer voice assistants built on LLMs.
NatBot: GPT-3-Driven Browser Automation
NatBot is an early LLM-driven browser automation bot by Nat Friedman — it takes a natural language task, drives a Chromium browser via Playwright, and completes multi-step web tasks. A 2022 proof-of-concept for what later became the AI browser agent category.
GPT-3 + Python Interpreter (gpt.py)
A 2022 Replit demo by Sergey Karayev showing GPT-3 armed with a Python interpreter — doing exact arithmetic, making API requests, and answering questions that pure text generation gets wrong. An early, concrete preview of what LLM tool use would look like.
GPT-3 and Arithmetic (MIT LINGO Lab)
MIT LINGO Lab's analysis of GPT-3's arithmetic abilities — probing how and when it succeeds or fails at basic math, and what this reveals about how language models represent numerical reasoning. Relevant to understanding the difference between pattern matching and genuine computation.
Writesonic: AI Writing Assistant
Writesonic is a GPT-3-powered AI writing tool focused on marketing copy, blog posts, and ad creative. One of the early AI writing SaaS products that demonstrated commercial viability for LLM-powered content generation.
Modern NLP with Large Language Models (Sinan Ozdemir, Maven)
Sinan Ozdemir's Maven cohort course on modern NLP with GPT-3/4 and BERT — covering information retrieval, multi-task pipelines, and prompt engineering. One of the early structured courses teaching practitioners how to build with LLMs.
GPT-3 Complete-Program Synthesis (Riley Goodside)
Riley Goodside demonstrates complete-program synthesis using GPT-3 via the 'format trick' — combining instruction prompts with contextually informative templates to generate entire programs deterministically. An early exploration of LLMs for structured code generation beyond autocomplete.
GPT-3 Long Instruction Following (Riley Goodside)
Riley Goodside demonstrates GPT-3 following a nearly 2,000-character instruction prompt precisely. An early illustration that LLMs can be reliable instruction followers with detailed context, countering the intuition that prompts should be kept short.
How to Play with the GPT-3 Language Model
Simon Willison's practical guide to getting started with GPT-3 — written in June 2022 when most developers still hadn't touched it. One of the clearest early explainers on the OpenAI API and what the model could actually do.
Prompts.ai: Advanced GPT-3 Playground
Prompts.ai was a community-built advanced GPT-3 playground that extended OpenAI's official interface with chaining, templates, and variable injection — an early tool for the prompt engineering community before ChatGPT made LLMs mainstream.
Codexplainer: Code Explanation via GPT-3
Codexplainer is a GPT-3-powered tool that explains arbitrary code snippets in plain English. One of the early AI code-explanation tools before GitHub Copilot Chat made this functionality mainstream.
Why GPT-3 Matters
Leo Gao's early analysis of why GPT-3 is qualitatively different from prior language models — written in May 2020 when GPT-3 was first announced. One of the clearer technical takes on what the scaling breakthrough meant, from someone who later worked on it.