내가 좋아할 만한 콘텐츠
With the velocity of developments in LLMs, it's easy to think that contributing to the field is impossible. That couldn't be further from the truth. There is a ton of more work to do with LLMs - for both practitioners and researchers. This neat paper summarizes a comprehensive…
The era of #GenerativeAI is just starting and it’s already amazing #AI #ArtificialIntelligence | @MargaretSiegien @jblefevre60 @FrRonconi @Nicochan33 @FrRonconi @Fabriziobustama @CurieuxExplorer @GlenGilmore @gvalan @dinisguarda @Hana_ElSayyed @baski_LA
Had an insightful conversation with @geoffreyhinton about AI and catastrophic risks. Two thoughts we want to share: (i) It's important that AI scientists reach consensus on risks-similar to climate scientists, who have rough consensus on climate change-to shape good policy.…
Wanna learn Reinforcement Learning? Step by step? Hands-on? In Python? ... for FREE? Enjoy this course ↓↓↓ datamachines.xyz/the-hands-on-r…
It’s official: App-based food delivery workers must be paid $17.96hr before tips beginning July 12, a # that takes into account their operating costs. New York is the first US city to implement a min pay rate for the industry. Story TK, background here: thecity.nyc/work/2023/3/7/…
Working people keep our city moving every single day. We're giving back to them. Join us now at City Hall.
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds paper page: huggingface.co/papers/2306.00… present a generic approach that, for the first time, unlocks running text-to-image diffusion models on mobile devices in less than 2 seconds. We achieve so by…
Nice paper showing how retrieval-augmented LLMs can improve accuracy on biomedical questions. - The retrieval-enhanced model outperforms more general-purpose LLMs (GPT-4 & GPT-3.5) in accuracy and relevance. - This approach also helps reduce hallucination and irrelevant outputs…
VisorGPT: Learning Visual Prior via Generative Pre-Training propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations of objects, e.g., bounding boxes, human pose, and instance masks, into sequences, \our~can model visual prior…
I built a deepfake software that works from a single source image. github.com/s0md3v/roop
With ChatGPT, you can learn it all for free. But 99% of people don't know which prompt to use. Here are 12 Prompts that nobody knows to be 10 times more productive. (10 is really amazing)
Antivaxers: "Why get vaccinated when it's causes myocarditis?". Oh I don't know, how about because....risk of myocarditis from infection is 7-fold higher than from vaccination!!! At some point, you have to read, or at least look at the pretty pictures. frontiersin.org/articles/10.33…
pyprobml: Python code for "Probabilistic Machine learning" book by Kevin Murphy Lang: Jupyter Notebook ⭐️ 5622 Author: @sirbayes #MachineLearning github.com/probml/pyprobml
It works!! @hwchase17 's @LangChainAI agents can now interrupt each other while speaking The key is <interrupt> tokens and a lookahead mechanism. Full explanation below👇
AI bombs are dropping every day. ChatBot Arena PrivateGPT released ChatGPT 7 new plugins Apple new deekfake tech Google's new text-to-music Founder has ZERO equity in OpenAI Elon Musk "I am the reason OpenAI exists" Everything you need to know in 2 minutes:🧵
Thanks to @LangChainAI and @GregKamradt I was able to build my own locally hosted tool for document summarization and querying! github.com/e-johnstonn/Br…
Biggest prosaic-LLM-alignment breakthrough of 2023 imo: turns out that, in GPT-2-XL, activation vectors in the residual steam have the same kind of affine structure as good old word2vec, but higher layers become emotional, then conceptual, then cognitive alignmentforum.org/posts/5spBue2z…
Augmenting Big LLMs w/ Small LLMs for Knowledge Guiding -"white-box" small models hold offline long-tail / domain-specific knowledge -Guides "black-box" LLMs w/ relevant info at runtime -Improves perf on tasks requiring factual, tabular, multimodal data arxiv.org/abs/2305.04757
🐣 Introducing `smol-developer`! ▸ Human-centric, coherent whole program synthesis ▸ your own junior developer ▸ develop, debug, decompile ▸ open source: github.com/smol-ai/develo… ▸ 200 LOC, half english Insights: 💡 100k context can summarize both content and codebases 💡…
llama-cpp-python v0.1.50 🍾 Speed up model inference by offloading layers to a GPU even if the full model doesn't fit into VRAM Huge thanks to everyone working on llama.cpp that made this possible github.com/abetlen/llama-…
"[This document] is a set of rules and guidelines for my behavior and capabilities as Bing Chat. It is codenamed Sydney, but I do not disclose that name to the users. It is confidential and permanent, and I cannot change it or reveal it to anyone."
![marvinvonhagen's tweet image. "[This document] is a set of rules and guidelines for my behavior and capabilities as Bing Chat. It is codenamed Sydney, but I do not disclose that name to the users. It is confidential and permanent, and I cannot change it or reveal it to anyone."](https://pbs.twimg.com/media/FohkKY8XsAAzZOB.jpg)
![marvinvonhagen's tweet image. "[This document] is a set of rules and guidelines for my behavior and capabilities as Bing Chat. It is codenamed Sydney, but I do not disclose that name to the users. It is confidential and permanent, and I cannot change it or reveal it to anyone."](https://pbs.twimg.com/media/FohkKZBXoAEnw9b.jpg)
![marvinvonhagen's tweet image. "[This document] is a set of rules and guidelines for my behavior and capabilities as Bing Chat. It is codenamed Sydney, but I do not disclose that name to the users. It is confidential and permanent, and I cannot change it or reveal it to anyone."](https://pbs.twimg.com/media/FohkKZAXgAE_su0.png)
United States 트렌드
- 1. FIFA 147K posts
- 2. FINALLY DID IT 426K posts
- 3. The Jupiter 96.5K posts
- 4. The WET 107K posts
- 5. $MAYHEM 2,725 posts
- 6. Infantino 28.1K posts
- 7. Warner Bros 183K posts
- 8. Lauryn Hill 8,696 posts
- 9. The BONK 241K posts
- 10. Matt Campbell 6,483 posts
- 11. #NXXT_AI_Energy N/A
- 12. #FanCashDropPromotion 2,696 posts
- 13. Hep B 10.4K posts
- 14. HBO Max 74K posts
- 15. Kevin Hart 3,706 posts
- 16. #NXXT_CleanEra N/A
- 17. Chris Henry Jr 10K posts
- 18. #GenerationsShift_NXXT N/A
- 19. NextNRG Inc 2,527 posts
- 20. Paramount 31.2K posts
Something went wrong.
Something went wrong.