sandkoan

How curious: I have a small children's book I picked up at the California Academy of Sciences entitled, "The ABCs of particle physics," made by a joint collaboration between Fermilab and SLAC [1], and here I find another poem in the same vein!

[1] https://www.symmetrymagazine.org/article/the-abcs-of-particl...

From what I can see, they download the repo to their server, generate per-function semantic embeddings (which will no doubt cost them at scale) [1], then use some combination of GPT-3 and Codex prompted with something like "Here's the source code of a git repo. Answer the following questions about it: {USER_QUESTION}."

[1] https://beta.openai.com/docs/guides/embeddings

This is good fun. In the same spirit as something I threw together recently [1], that runs broken code (with un/misdefined functions and variables), and repairs it using a combination of stacktraces and comments fed to GPT-3.

[1] https://news.ycombinator.com/item?id=34230238

There might be a reason for that: https://nautil.us/issue/47/consciousness/the-kekul-problem.

Looks pretty cool! I've been working on something similar, but was a bit discouraged by market saturation in the universal search space.... How does this compare to something like, say, Glean?

Here's an updated link: https://huggingface.co/spaces/sandkoan/athelas. Athelas reads stacktraces and whatnot to determine how to repair broken code, and returns what it thinks the code should be, taking into account logic errors, etc.

Woah! I've been facing the same problems with pyannote+whisper for diarization+transcription, and, coincidentally, was just experimenting with combining NeMO and whisper. Do you happen to have a repo for this? Would be invaluable.

Edit: Nevermind, found the link: https://colab.research.google.com/drive/1X5XTiob6irFq8NJM831...

For the record, Python didn't have a case or when statement. It does now, recently added to version 3.10.

Is there a particular reason that web-based 3d editors failed to find a market? Is it just that those working in the modelling space are already well-versed in actual editing tools, so they don't really have a need for something like this, while the average nontechnical/nonspecialist consumer has little reason to edit 3d? Because Figma seems to have taken off despite having largely a similar model.

Would a collaborative version of the 3d editor concept be more of a success?

Everything required to make the tool already exists.

Just ran your exact query through OpenAI's Codex (model: code-davinci-002), and this was the result:

SELECT * FROM customers WHERE city = 'London' AND purchase_date BETWEEN '2019-01-01' AND '2019-01-31' AND product_name = 'laptop' AND product_ram > 16 AND coupon_percentage BETWEEN 10 AND 25 ORDER BY price_paid DESC;

I'd say it's pretty damn accurate.