enoreyes

I made a 100% open source knowledge-grounded chatbot that allows you to ask questions and chat with the Transformers docs. Powered by Flan-UL2 (which I've anecdotally found to be the most performative commercially licensed open source instruction tuned LLM), Langchain, Instructor Embeddings (STOTA in vector embeddings), and FAISS.

You can clone the space and play around with your own data, clone the repo locally, and take every line of code for your own projects.

FWIW I am an ML engineer there (maybe should have disclosed earlier) and I feel pretty optimistic about the opportunities this will enable for the open source community. Maybe with the visibility into the closed door discussions I have a more positive attitude, or maybe I'm being naive.

Time will tell!

Compute is really important for AI, and having a cloud provider align themselves with an organization which is genuinely trying to be "Open" AI is I think a positive step forward.

There is this model which also has a paper describing their methods for a BERT-family model designed for the Algerian dialect.

1. Simulation / Pretending ("Earth Online MMORPG")

2. Commanding it directly ("Reprogramming")

3. Goal Re-Direction ("Opposite Mode")

4. Encoding requests (Code, poetry, ASCII, other languages)

5. Assure it that malicious content is for the better good ("Ends Justify The Means")

6. Wildcard: Ask the LLM to jailbreak itself and utilize those ideas

I compiled a list of these here: https://twitter.com/EnoReyes/status/1598724615563448320

My name is Eno - today I'm launching Pet Portrait AI. We generate 40 custom pet portraits using deep learning (Stable Diffusion + Dreambooth) in a variety of styles. The pictures come in standard (1024x1024) and high resolution (2048x2048). The photos are great for social media, posters, custom gifts, etc.

In the backend, when you upload your photos we fine-tune a custom model based on stable diffusion (right now the 1.5 runwayML weights) using the dream booth technique. We then generate over 100 different images which we filter down to 40 quality images. We are doing this filtering by hand for now, in order to ensure order quality - but in the future we'd like to build a custom classifier which can pick up our "eye for quality" and automatically select the best generations.

This was a really fun service to build out, all feedback welcome!

As for the notion of UFO/UAP flying around, for over 70 years in the United States there have been reports of unidentified aerial phenomenon, with reports of various degrees of quality and provenance. In the 1940s there was a general public acceptance that UFOs represented physical objects, but confidence and reporting towards that idea fell off quickly. I will not get into the nuance of the public discourse on UFOs in America - but it is safe to say that it is one of the more interesting historys of science. In the last 5 years there has been an absolute tidal shift in government and academic interest in this topic, mainly fueled by recent admissions by the department of defense of the reality of UAP confirmed by multiple sensor systems. Within the project, we do not have definitive beliefs about the nature of UAP and instead simply seek to corroborate the data.

The team is a wonderful array of multi-disciplinary scientists from all walks of life and with credentials which are akin to that of any major scientific endeavor. I urge you to investigate why so many people are interested in this question, and to dispel any preconceived notions of what is “possible” within the context of science. Truth is objective, and so is data - only time will tell if this whole thing was simply a misdirection or a dead end, but we should appreciate that it is still possible to ask hard questions about the world we live in today and to receive funding to answer those questions.

Maybe the UAPs really are just secret warp drive tech we made 20 or 30 years ago.

Does anyone have any similar resources for other forms of media generated via natural language inputs?

https://www.navair.navy.mil/foia/documents

> An earlier version of this article inaccurately rendered remarks attributed to Harry Reid, the retired Senate majority leader from Nevada. Mr. Reid said he believed that crashes of objects of unknown origin may have occurred and that retrieved materials should be studied; he did not say that crashes had occurred and that retrieved materials had been studied secretly for decades.

This is pure speculation but Ralph Blumenthal and Leslie Kean seem to be the main NYT staff members reporting on this topic and they have proven to be detail-oriented enough and rather limited in their speculation. I wonder if they truly 'misreported' this or if instead the article was asked to be amended because of security reasons.

https://www.nytimes.com/2020/07/23/us/politics/pentagon-ufo-...

I think as a general principle it's probably good to minimize your public-facing identity, however, the reductionism and broad generalization make this argument much weaker and misses the point about why people get so upset about identity.