HackerTrans
TopNewTrendsCommentsPastAskShowJobs

alt-glitch

no profile record

Submissions

Indian ISPs block Supabase due to a ministry order

twitter.com
15 points·by alt-glitch·5 ay önce·1 comments

Speedrunning an RL Environment

sidb.in
2 points·by alt-glitch·9 ay önce·0 comments

LangGraph and Composio Achieved 48.6% on SWE Bench

blog.langchain.dev
9 points·by alt-glitch·2 yıl önce·0 comments

Rabbit R1 reverse engineered to run on Android

twitter.com
24 points·by alt-glitch·2 yıl önce·4 comments

I scraped all of OpenAI's Community Forum

julep-ai.github.io
310 points·by alt-glitch·2 yıl önce·59 comments

comments

alt-glitch
·2 yıl önce·discuss
I wonder if I can hook up `scrcpy` with this and give it control over an Android. Can it drag the mouse? That'd be needed to navigate the phone at least.
alt-glitch
·2 yıl önce·discuss
I believe a community forum is absolutely vital for an "ecosystem" company. There needs to be a town square where people can discuss ideas and share feedback about that particular ecosystem.

OpenAI has a pretty active forum with moderators replying and helping out all the time.
alt-glitch
·2 yıl önce·discuss
Hey! Happy to chat over email/X more closely and help you out.

Nomic Atlas automatically generates the labels here. There could be different variations of posts involving the Python Packages.

But I did some manual digging & here's what I found; Heading over to the map and filtering by posts around "Python Packages" leads to around 900 posts.

Sharing a few examples which do talk about people's posts related to the python package:

- https://community.openai.com/p/701058 - https://community.openai.com/p/652075 - https://community.openai.com/t/32442 - https://community.openai.com/p/143928

Note: My intuition is that most of the posts are very basic, probably user errors like "No API Key Found" etc.
alt-glitch
·2 yıl önce·discuss
This is definitely a workflow we can package into something open-source.

I wonder how the community moderators would like it.
alt-glitch
·2 yıl önce·discuss
Neat find! That's actually a cluster of all the system messages notifying users about closing and re-opening of the thread. That's why they're so tightly clustered.

I believe the naming isn't perfect for this, but this was all automatic topic modelling!

Example: [1]: https://community.openai.com/t/read-this-before-posting-a-ne...
alt-glitch
·2 yıl önce·discuss
We were really heading someplace with The Semantic Web aka The Real Web 3.0 [1]

Alas we have to fight against the machines in order to properly read the internet thru machines.

I believe Discourse knowingly keeps its data easy to scrape though, so kudos to them!

[1]: https://en.wikipedia.org/wiki/Semantic_Web
alt-glitch
·3 yıl önce·discuss
For a full text + semantic search, I'm building Nous! It's a search engine for your bookmarks.

- check it out here: nous[.]fyi
alt-glitch
·3 yıl önce·discuss
Super cool! I had a similar idea where I wanted to create such clones of some of my friends (with consent ofc) and see how well they know me. To extend your clone even more, you can also throw in every piece of digital text you have into this, eg. emails, notes, essays, blogs etc. I'm super down to work on LLM clones like these!

edit: I actually started a little work on this. If you wanna export more messages than the limited 40k, you can use [0]. I did and I have every text I've ever sent since I had WhatsApp.

[0]: https://github.com/YuvrajRaghuvanshiS/WhatsApp-Key-Database-...