Picking your general-purpose AI

Also:

https://www.oneusefulthing.org/p/doing-stuff-with-ai-opinionated-midyear

Thus, that module was deprecated in favor of Nelson's OpenAPI::Client::OpenAI module. Throw the 13K+ lines OpenAPI spec for OpenAI at it and it just works. Further, the module is pretty much a single Perl class rather than a bunch of hand-crafted code.

CPAN authors know it can be hard to keep modules up-to-date (mea culpa, mea culpa!) and this module is no exception. I need this module so I offered to collaborate and created a PR to update it to version 2.0.0 of the OpenAI spec. It now passes all the tests (for those wondering, you need an OpenAI key and it costs $0.04 USD to run the test suite).

In trying to build a Whisper pipeline for that, I found that I couldn't. There was a PR for Whisper support for the older module, but for the newer one, I can't figure out how to get it to issue a request with multipart/form-data support. I've noted the issue in the PR.

In the near future, transforming text over an entire document will become as commonplace as filtering images.

Up until now, text editors have been focused on input. The next evolution of text editors will make it easy to alter, summarize and lengthen text. You’ll be able to do this for entire documents, not just individual sentences or paragraphs. The filters will be instantaneous and as good as if you wrote the text yourself. You will also be able to do this with local files, on your device, without relying on remote servers.

In a “A camera for ideas”, I coined the term synthography to describe synthetic images created with generative models.

Text generator is a handy plugin for Obsidian that helps you generate text content using GPT-3 (OpenAI). - GitHub - nhaouari/obsidian-textgenerator-plugin: Text generator is a handy plugin for Obsidian that helps you generate text content using GPT-3 (OpenAI).

Use Text Generator to generate ideas, attractive titles, summaries, outlines, and whole paragraphs based on your knowledge database.

A great deal of my learnings and inspiration comes from the great content from Yubin Ma at AiTuts, where you can learn more about prompting and view a myriad of examples.

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue) - GitHub - abi/screenshot-to-code: Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

I've watched the 4 videos from 3blue1brown on neural nets. The web and youtube are awash with mediocre videos on Large Language Models. I'm looking for a good one.

This is part of a longer series but is maybe the single best video I know of on the topic:
https://youtu.be/kCc8FmEb1nY?si=zmBleKwlpV06O3Mw

I thought this video from Steven Wolfram was also quite good:
https://www.youtube.com/live/flXrLGPY3SU?si=SrP1EJFMPJqVCFPL

An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨 - GitHub - varunshenoy/opendream: An extensible, easy-to-use, and portable diffusion web UI 👨‍🎨

A CLI utility and Python library for interacting with Large Language Models, both via remote APIs and models that can be installed and run on your own machine.

A deep-dive into machine learning embeddings.

Covering the state of play as of Summer, 2023

Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.

In May 2023, Eric Hartford, a machine learning engineer authored a popular blog post “Uncensored Models” providing his viewpoints to the merits of uncensored models, and how they are created. It’s a great read!

This post will give some example comparisons running Llama 2 uncensored model vs its censored model.

https://erichartford.com/uncensored-models