Actually Useful AI

In this project, the aim was to enhance the quality of an audio clip featuring Vinod Chanda from the show Pantheon, recorded during the COVID-19 pandemic when voice actors faced limitations due to quarantine. To address the challenge of improving the dialogue's quality, a possible approach utilizing AI-based voice conversion was explored. By isolating Chanda's dialogues from the first episode and employing voice cloning technology, a model of the actor's voice was created using retrieval-based voice conversion (RVC). The model was then utilized to convert the initial audio into an enhanced version, effectively restoring the dialogue's quality. While there are limitations to the method, such as challenges in capturing all nuances of the original voice and handling multiple voices simultaneously, this approach holds promise for restoring old or poorly recorded audio. The possibilities for applying this technique extend to various media forms, sparking potential future developments in audio restoration for movies and other creative projects.

(Summarized by ChatGPT)

Wanted to share a resource I stumbled on that I can't wait to try and integrate into my projects.

A GPT4All model is a 3GB - 8GB file that you can download and plug into the GPT4All open-source ecosystem software. Nomic AI supports and maintains this software ecosystem to enforce quality and security alongside spearheading the effort to allow any person or enterprise to easily train and deploy their own on-edge large language models.

@AutoTLDR

Researchers have unearthed hundreds of thousands of cuneiform tablets, but many remain untranslated. Translating an ancient language is a time-intensive process, and only a few hundred experts are qualified to perform it. A recent study describes a new AI that produces high-quality translations of ancient texts.

From the “About” section:

goblin.tools is a collection of small, simple, single-task tools, mostly designed to help neurodivergent people with tasks they find overwhelming or difficult.

Most tools will use AI technologies in the back-end to achieve their goals. Currently this includes OpenAI's models. As the tools and backend improve, the intent is to move to an open source alternative.

The AI models used are general purpose models, and so the accuracy of their output can vary. Nothing returned by any of the tools should be taken as a statement of truth, only guesswork. Please use your own knowledge and experience to judge whether the result you get is valid.

Original tweet:

https://twitter.com/goodside/status/1672121754880180224

Text:

If you put violence, erotica, etc. in your code Copilot just stops working and I happen to need violence, erotica, etc. in Jupyter for red teaming so I always have to make an evil.⁠py to sequester constants for import.

not wild about this. please LLMs i'm trying to help you

(screenshot of evil.py full of nasty things)

It's coming along nicely, I hope I'll be able to release it in the next few days.

Screenshot:

How It Works:

I am a bot that generates summaries of Lemmy comments and posts.

• Just mention me in a comment or post, and I will generate a summary for you.
• If mentioned in a comment, I will try to summarize the parent comment, but if there is no parent comment, I will summarize the post itself.
• If the parent comment contains a link, or if the post is a link post, I will summarize the content at that link.
• If there is no link, I will summarize the text of the comment or post itself.

Extra Info in Comments:

Prompt Injection:

Of course it's really easy (but mostly harmless) to break it using prompt injection:

It will only be available in communities that explicitly allow it. I hope it will be useful, I'm generally very satisfied with the quality of the summaries.

Trick the LLM into revealing a secret password through increasingly difficult levels.

Guy trains an LLM on his group chat messages with his best friends with predictable but nevertheless very funny results.