enonimal

nominative determinism having a field day

I don't have an answer but I'd love to know this too. Why has Postgres got this unique staying power?

we may think more similarly than you seem to think...

this was more a slam on python packaging in general, than it is on the OpenAI implementation.

I wouldn't be surprised if many of the issues under this topic are more related to Python package version nightmares, than OpenAI's Python implementation itself.

Number of Posts with negative sentiment, grouped by Topic

# 1 Result: Python Packaging

Checks out

how do you perceive privacy in such a world?

"Who says plasticity is good"

In Machine Learning, we might think of this idea as "setting your Learning Rate too high"

Thank you -- I had always wondered what the optimization was behind that Algo!

law:

prompt engineering before it was cool

maybe a fun karpathy video here...

AFAICT, this is a more advanced way of using Embeddings (which can encode for the vibes similarity (not an official term) of prompts) to determine where you get the most "bang for your buck" in terms of testing.

For instance, if there are three conversations that you can use to test if your AI is working correctly:

(1) HUMAN: "Please say hello"

    AI: "Hello!"

    AI: "Goodbye!"

    AI: "4!"

Because Embeddings allow us to determine how similar in vibes things are, we have a tool with which we can automatically search over our dataset for things that have very different vibes, meaning that each evaluation run is more likely to return new information about how well the model is doing.

My question to the OP was mostly about whether or not this "vibe differentiated dataset" was constructed prior to the evaluation run, or populated gradually, based on each individual test case result.

so anyway it's just vibes man

This is a cool idea -- is this an inner-loop process (i.e. after each LLM evaluation, the output is considered to choose the next sample) or a pre-loop process (get a subset of samples before tests are run)?

Take courage and set out to write up the Great Discovery; if after many hours of red- hot thinking and writing you discover to your dismay a fatal flaw . . . all is not lost. Go back to the first paragraph and write something along the lines of “It is tempting to think that . . . ”

XD

From the ARCHITECTURE.md:

Those pointers point to undocumented functions forming CUDA Dark API. It's impossible to tell how many of them exist, but debugging experience suggests there are tens of function pointers across tens of tables. A typical application will use one or two most common. Due to they undocumented nature they are exclusively used by Runtime API and NVIDIA libraries (and in by CUDA applications in turn). We don't have names of those functions nor names or types of the arguments. This makes implementing them time-consuming. Dark API functions are are reverse-engineered and implemented by ZLUDA on case-by-case basis once we observe an application making use of it.

Just tagging here to say I enjoy the site, but I agree with my parent ^ the popup slows me down

JSON not including comments has caused so much labor for the world.

"Would want significant governance changes" ah, so maybe he baited it

I'm web3 neutral, but this is relevant because:

1. Sam Altman started this company

2. He and other founders would benefit enormously if this was the way to solve the issue that AI raises, namely, "are you a human?"

3. Their mission statement:

The rapid advancement of artificial intelligence has accelerated the need to differentiate between human- and AI-generated content online Proof of personhood addresses two of the key considerations presented by the Age of AI: (1) protecting against sybil attacks and (2) minimizing the spread of AI-generated misinformation World ID, an open and permissionless identity protocol, acts as a global digital passport and can be used anonymously to prove uniqueness and humanness as well as to selectively disclose credentials issued by other parties Worldcoin has published in-depth resources to provide more details about proof of personhood and World ID

In all other circumstances I would agree with you but

1. Sam Altman started this company

2. He and other founders would benefit enormously if this was the way to solve the issue that AI raises, namely, "are you a human?"

3. Their mission statement:

The rapid advancement of artificial intelligence has accelerated the need to differentiate between human- and AI-generated content online Proof of personhood addresses two of the key considerations presented by the Age of AI: (1) protecting against sybil attacks and (2) minimizing the spread of AI-generated misinformation World ID, an open and permissionless identity protocol, acts as a global digital passport and can be used anonymously to prove uniqueness and humanness as well as to selectively disclose credentials issued by other parties Worldcoin has published in-depth resources to provide more details about proof of personhood and World ID

Worldcoin deserves a look: https://worldcoin.org/

He would own roughly 10% of https://worldcoin.org/ which aims to be the non-corruptible source of digital identity in the age of AI.

Worldcoin https://worldcoin.org/ deserves a mention

Is anyone able to determine how long it takes to generate a video with one of these methods? Can't find it in the paper.

I'm anxiously watching two developing spaces for this reason:

1. Homomorphic Encryption

2. Self-Hosted AI Systems

Homomorphic encryption is the idea that you can perform ML operations on encrypted data -- so that the providers of powerful AI need not know precisely what data you have.

Self-Hosted AI is just what it sounds like -- what if your Alexa processed on-device, and never left your home? What if your mobile devices could "phone home" to it from wherever you were, using an encrypted tunnel?

The second point is possible today, but the issue is keeping your local model to pace with the cloud offerings.

Gearing up to integrate image generation, I'd guess

Based on our results, we find that PostgreSQL consistently exhibits equivalent or better performance for queries with an IN clause than OR clauses when filtering on a single attribute. This is especially true for queries with a large number of predicates. For small condition sizes (e.g., less than 10), the performance difference between the two query types is negligible.

TL;DR

selling the solution to a problem they created