- The Neuron
- Posts
- šŗ 747 word mega prompt
šŗ 747 word mega prompt
PLUS: Sarah Silverman is MAD at OpenAI š¤¬...
Welcome, humans.
Threads (Metaās Twitter clone) raced past ChatGPT to become the fastest product to 100 million users.
We shouldāve known: celebrity latte updates are more important than superintelligent chatbots. āļøš¤
Hereās whatās going on in AI today:
An awesome prompt we found for ChatGPTās Code Interpreter.
Sarah Silverman is suing OpenAI and Meta.
Googleās medical AI is being tested in hospitals.
Journalists are raging over AI-generated articles.
ChatGPTās Code Interpreter Isnāt Just Good With Data š
Weāre obsessed with ChatGPTās Code Interpreter.
It cranks out data analyses at the level of an average data analyst in seconds (plus itās also always behind a computer screen ā get it?!). Itās so good that some suspect itās powered by a model even more advanced than GPT-4.
(We highly recommend this comprehensive prompt for generating the best visuals).
But itās not just helpful with data. Code Interpreter uses code to understand your files which means it can also tinker with them. This includes:
basic video editing (see example).
extracting text from images.
crafting entire games (walkthrough).
designing QR codes.
And the tech industryās all time favorite: file type conversions. It does this all by running Python scripts.
But hereās the catch: If youāre an expert in design/data/CS, Code Interpreterās features might feel limited. And, like ChatGPT, Code Interpreter might try to bullsh*t you when confused, (often by creating nonexistent data).
Here are a few expert prompting tricks to harness Code Interpreter from our guru Prof Ethan Mollick:
Feed it text files or plain text, not PDFs (too long).
Encourage it to ājust tryā if it says it canāt do something.
Engage in back-and-forth vs. lengthy prompts.
P.S. Weāre gearing up to teach a course on how to automate your entire workflows using Code Interpreter and GPT-4. Sign up for our waitlist here!
Authors Are Suing OpenAI & Meta For Copyright Infringement š
Sarah Silverman, by Midjourney
Comics once worried about hustlers stealing their punchlines. Now itās AI behemoths.
Sarah Silverman and two other authors are suing OpenAI and Meta for training ChatGPT and LLaMA on their (copyrighted) literary works.
Their line of defense:
LLaMA is trained on ThePile, which is trained on a shadow library called Bibliotik, which is known to be āflagrantly illegalā.
Oh, and the models are like wayyy too good at summarizing their books.
This isnāt a one-off.
Just last week, two different authors sued OpenAI. Artists are locking horns with Midjourney and Stability AI. Hollywood writers are protesting against AI.
Hereās our take: Itās glaringly obvious that these models are gulping down content without asking permission.
BUT: itās kinda like illegally streaming films ā everyone does it and no one ever gets in trouble. Expect more lawsuits and perhaps a few settlements, but defending content in the digital realm is becoming a losing battle.
Around the Horn š¦
Googleās medical chatbot, Med-PaLM 2, is being tested in hospitals.
A deepfake video ad of financial journalist Martin Lewis shilling an investment circulated on Facebook.
Gizmodo is getting pushback from journalists for its AI-generated articles.
How the folks at Mithral Security tricked an AI (PoisonGPT) into spreading fake news.
Treats To Try šæ
GPT-Migrate lets you migrate migrate your codebase from one language to another one.
Train your AI model once and deploy on any cloud with NVIDIA and Run:ai.
Pi, your personal AI chatbot, is now available on iOS.
Generate cookies for your website using Biscuits.ai.
We curated the top 27 tools you need for work in our āTop Tools For Businessā!
Monday Meme š
A Cat's Commentary š»
That's all we have for today. Get started using AI with our free Intro To ChatGPT mini-course!
See you cool cats on Twitter if you're there: @nonmayorpete & @noahedelman02.
What'd you think of today's email? |