Promptable.ai (@PromptableAI) header
Promptable.ai (@PromptableAI) profile picture

OSS AI Apps in Typescript. https://teapawt.org/t.co/6mNjOes1QR https://teapawt.org/t.co/h8N5h6y6Pv

npm i promptable
Joined November 2022
Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)Photo by Promptable.ai (@PromptableAI)
Promptable.ai retweeted
Plugin #2 - HttpProxy Say goodbye to Postman + curl. Just ask ChatGPT to request whatever you want!
8
20
3
171
30,330
I couldn't wait for the ChatGPT Plugins waitlist. So, I built a quick chatbot that can access any official ChatGPT Plugins by dynamically parsing their OpenAPI spec.⚡️ Built using wellknown.ai and @guardrails_ai. Link: colab.research.google.com/dr…
8
43
5
331
71,400
Promptable.ai retweeted
I built a chatbot to talk to my friends Blog post instead of reading it 🫣-> Okay so @AlistairPullen posted a post about the ChatGPT api, but I didn't want to read it all 🤣. teapawt.org/AlistairPullen/status/… So I built a chat bot in Promptable.js to talk with his article:
I’ve had early access to the ChatGPT API for the past couple of months, here are all of the learning’s I’ve found that have made it into our product buildt.ai/blog/vm3qozd4qfrbb…
5
3
4
64
41,889
Promptable.ai retweeted
Use the NEW ChatGPT API in Typescript with @PromptableAI Usage -> System: "You're a helpful assistant:" User:💬 Assistant:💬 User: 💬 Repo: github.com/cfortuner/prompta… Example:
8
8
4
89
16,585
Promptable.ai retweeted
What is a large language model? How can it be used to enhance your business? @ROWGHANI, Managing Director of YC Continuity, talks with @RazRazcle, CEO of @humanloop, about the cutting-edge AI powering innovations today—and what the future may hold. ▶️ youtu.be/hQC5O3WTmuo
2
21
6
104
62,933
Claude, @AnthropicAI's powerful ChatGPT alternative, was trained with "Constitutional AI". Constitutional AI is particularly interesting since it uses less human feedback than other methods, making it more scalable. Let's dive into how Constitutional AI works in 13 tweets!
18
113
5
883
320,786
Promptable.ai retweeted
Time to update my resume title to Prompt Typesafety Engineer.
Coming soon... ✨Load your prompts from Promptable.ai ✨ ...and import them as Typesafe, Prompt templates! Magic🪄
1
3
916
🚀 built with @PromptableAI
💡 AI-based seeding 🌱 @justinliang1020 built GPT-SEED as a quicker way to seed databases for rapid development. ▶️ In this demo, Justin showed us how to seed data in Prisma with GPT-SEED. youtu.be/bLC7sS-9x20?t=1171
1
3
1,053
Promptable.ai retweeted
💡 AI-based seeding 🌱 @justinliang1020 built GPT-SEED as a quicker way to seed databases for rapid development. ▶️ In this demo, Justin showed us how to seed data in Prisma with GPT-SEED. youtu.be/bLC7sS-9x20?t=1171
1
4
1
33
6,378
This is awesome! Previously, I had to manually copy-paste my prompt from Promptable.ai into my library calls to promptable.js. Whenever I made a change to one, I had to go and change the other. Now, it's all automated.
Coming soon... ✨Load your prompts from Promptable.ai ✨ ...and import them as Typesafe, Prompt templates! Magic🪄
1
1
863
The @PromptableAI universal starter is done. Countdown to release. Stay tuned.
2
7
910
I am coming out of a week-long, 20h/day fugue state. All my toy apps now rewritten in TS + @PromptableAI, and I am approaching optimization. I am now asking you, dear reader, for links relating to prior art regarding LLM prompt-based extraction from context. My faves in 🧵 :
2
4
1
27
6,720
Ok so this is happening. @expo universal starter for @PromptableAI . Still on the making BUT small footprint. Coming out soon.
6
26
2,827
My first blog post on Prompt engineering 🤖🍾. Go through all the first steps to get to build a hotel booking chatbot with @OpenAI GPT-3 API and @PromptableAI bidah.hashnode.dev/prompt-en…
4
8
606
What started out as a mini hackathon to learn d3, turned into a pretty fun project where I can use GPT to automate data analytics. Here's a little web-app I built that uses GPT to turn any arbitrary CSV file into a dashboard of data visualizations (using d3 library)
15
72
5
662
173,663
Promptable.ai retweeted
Why Python won't be the language of LLMs. (and what will) Python has long had a monopoly on data workflows — everything from data analysis to data science to machine learning. Anything that can't be done in SQL is done in Python. But Python won't be the language for LLMs. Why? → Simple interfaces served over the web. Whether or not many companies will end up self-hosting these models, the interface remains simple. Sure, you can use OpenAI's python library to make a call to the completion API, but you can just as quickly run a cURL command to do the same. Or an HTTP request from any language. → Data-lite (preparing the model). Before, you had to clean your data and convert it to specific data structures — e.g., a model might accept an embedding as the input. These data structures were often heavy and complex to pickle or serialize over the wire, so they stayed in Python. Now, natural language fits cleanly in a string (or a binary image or audio file without special encoding). → Data-lite (calling the model). While some companies may still fine-tune and pack their data into these models somehow, many other workflows can be done with a small amount of data (e.g., in JSONL), a multi-line string of examples (few-shot), or nothing at all (zero-shot). High latency also means that developers will move the model calls as close to the application as possible ("on the edge"). → Performance-critical libraries are not written in Python. Most of the low-level libraries are simply Python wrappers over C++ or Rust. In theory, these can be called from other languages. Language boundaries are blurring. So what becomes the language of LLMs? JavaScript, by the numbers. But in reality, no language at all. Why? → Deployed on the edge. Lower latency means happier users. I imagine there will be providers who offer edge-colocated LLMs for fast interference. → For application end-developers. You won't need a complicated data pipeline to start with or call LLMs. You don't need a data science certificate to call these models either (it's just plain text, for now). → Type safety. LLMs can return any schema (or none at all). Instead of parsing plain text, developers will prefer to restrict LLM calls to a known schema. What language would be best for this? TypeScript (too complex and verbose to do with JSON schema).
18
31
12
220
64,653
This prompt in the @PromptableAI JS library changed the way I think about LLMs. github.com/cfortuner/prompta… I am moving towards a paradigm of thinking of prompts as either generation, extraction, transformation or classification tasks -- such a powerful set of abstractions.
2
8
1
59
5,706
Promptable.ai retweeted
1k stars in 1 week! 🙏❤️ @PromptableAI Come build ai tools in Typescript with us -> discord.gg/8GKSYtSt
2
5
2
45
6,681