Ray Hung
@ruize_h
Building Socratic Mind | SWE Intern @ Databricks, Scale AI, Meta, Amazon | On Deck Fellow | | CS @GeorgiaTech
You might like
Fei-Fei Li (@drfeifei) on limitations of LLMs. "There's no language out there in nature. You don't go out in nature and there's words written in the sky for you.. There is a 3D world that follows laws of physics." Language is purely generated signal.
Columbia CS Prof explains why LLMs can’t generate new scientific ideas. Bcz LLMs learn a structured “map”, Bayesian manifold, of known data and work well within it, but fail outside it. But true discovery means creating new maps, which LLMs cannot do.
The problem with modern dating is everyone is looking at y intercept when they need to be focusing on slope. No one is a finished product in their 20s (or 30s or even 40s).
Europe created a monster: • Forces annoying popups on EVERY website • Costs businesses €10 BILLION+ in compliance • Provides ZERO actual privacy protection The annoying truth about how one dumb "feel good law" is slowing European innovation 🍪:
META JUST KILLED TOKENIZATION !!! A few hours ago they released "Byte Latent Transformer". A tokenizer free architecture that dynamically encodes Bytes into Patches and achieves better inference efficiency and robustness! (I was just talking about how we need dynamic…
The best explanation of curse of dimensionality I've seen. MFML 095 - The curse of dimensionality youtu.be/oTSj0TTDSPI?si… via @YouTube
youtube.com
YouTube
MFML 095 - The curse of dimensionality
I’m thrilled to share Emergent Mind’s new AI research assistant, a tool that makes it incredibly easy to learn about new computer science research. You can search for papers, topics, authors, or questions, and it will then find the most relevant computer science papers on arXiv…
The #ToolsCompetition is open to competitors of all backgrounds, even students. Last cycle, @ruize_h, a @GeorgiaTech master's student, won for a tool that uses AI to conduct oral assessments. Learn more. tinyurl.com/2hx8uwkf
Ray (Jui-Tse) Hung (@ruize_h), a master's student in computer science, is the lead developer of The Socratic Mind, an AI-powered tool that uses Socratic questioning to challenge students to explain, justify, and showcase their understanding of a subject. A year ago, he assisted…
In 2018, Sam Altman simultaneously managed YC(a $30B+ Startup Accelerator) , invested >$400M in startups on the side, and built the world’s best team of frontier AI researchers with Elon for Open AI. His answer to ‘How do you get so much done?’ is powerful. A thread 🧵
A good short read on how end to end encryption from Excalidraw. blog.excalidraw.com/end-to-end-enc…
We’re excited to launch a huge feature making @llama_index the framework for building knowledge graphs with LLMs: The Property Graph Index 💫 (There’s a lot of stuff to unpack here, let’s start from the top) You now have a sophisticated set of tools to construct and query a…
The USA only has ~4% of Earth’s population. Just 1% of Earth moving to America would overwhelm essential medical and other services. It’s not sustainable. As always, I’m very much in favor of *legal* immigration. Anyone smart, hardworking and honest should be welcome here.
20,000,000 illegal immigrants and that is just what we were able to record. That is more than 47 state's population! The insanity has to stop and we must secure our border now. martyforcongress.vote
apparently Google laid off their entire Python Foundations team, WTF! ( @SkyLi0n who is one of the pybind11 maintainers just informed me, asking what ways they can re-fund pybind11) The team seems to have done substantial work that seems critical for Google internally as well.…
I like being a generalist because Being an engineer makes me a better product person Being a product person makes me a better founder Being a founder makes me a better investor Being an investor makes me a better writer Being a writer makes me a better thinker Being a clear…
Just discovered github.com/romac/react-if This makes conditional rendering in React/Nextjs much easier to deal with!
blog.langchain.dev/multi-needle-i… Multi-Needle in A Haystack. Super interesting test done by the Langchain team. "Different patterns of retrieval failure - GPT-4 fails to retrieve needles towards the start of documents as context length increases."
Good paper by Netflix on cosine similarity. It goes back to building good RAG systems, which is hard. Before deploying these systems, you have to make intelligent decisions about chunking, hierarchical chunking, embedding, and even the algorithm for similarity look-up.…
I gave Claude 3 the entire source of a small C GIF decoding library I found on GitHub, and asked it to write me a Python function to generate random GIFs that exercised the parser. Its GIF generator got 92% line coverage in the decoder and found 4 memory safety bugs and one hang.
United States Trends
- 1. Rodgers 15.4K posts
- 2. Steelers 35.6K posts
- 3. Chargers 21.7K posts
- 4. #RHOP 6,039 posts
- 5. Schumer 186K posts
- 6. #HereWeGo 4,756 posts
- 7. Herbert 9,436 posts
- 8. Tim Kaine 9,773 posts
- 9. Resign 88.1K posts
- 10. #ITWelcomeToDerry 3,033 posts
- 11. Jaylen Warren 1,546 posts
- 12. Durbin 14.8K posts
- 13. Cornyn 10.2K posts
- 14. Cade Cunningham 4,407 posts
- 15. #snfonnbc N/A
- 16. Arthur Smith N/A
- 17. #90DayFianceHappilyEverAfter 1,800 posts
- 18. Rams 29.4K posts
- 19. Drummond 2,724 posts
- 20. Dicker Doinker N/A
You might like
-
Thanh Trinh ▫️
@0xthanh -
Karel van der Vyver
@karelvdvyver -
Pruitt
@0xPruitt -
Alex Hu 🐮
@AlexHu5_ -
Kenny Zhou
@_zhoukenny -
Jahnavi Kocha
@JahnaviKocha -
angad
@angad_ai -
Alex Young
@alex_j_young -
Benjamin Sturisky
@bsturisky -
Nick Nguyen
@nickngx -
Kaleb
@Kaleb0x -
Tiffany
@tiffdong -
ＡＬＢ Ξ ＲＴＯ🧪🧫
@albertolabs -
シオン
@zionmelson -
Evan Lee
@theEvanLee
Something went wrong.
Something went wrong.