e/ia – Intelligence Amplification
– Does not seek to build superintelligent God entity that replaces humans.
– Builds “bicycle for the mind” tools that empower and extend the information processing capabilities of humans.
– Of all humans, not a top percentile.
– Faithful to
TOOLS
-
Intelligence Amplification: Empowering Humans Over AI Superintelligence
By
–
-
DeepCache accelerates SDXL generation to 19 iterations per second
By
–
Faster vanilla SDXL with DeepCache in diffusers is interesting. @lucataco93 has got this up on Replicate: https://
replicate.com/lucataco/sdxl-
deepcache
… 1024×1024 at 25 steps seems to take ~3s on A100 (19it/s). More on DeepCache: https://
huggingface.co/papers/2312.00
858
… -
TestingCatalog Launches New AI News Assistant GPT
By
–
Meet TestingCatalog GPT, AI news & features assistant! 🗞
— 🚨 AI News | TestingCatalog (@testingcatalog) 7 janvier 2024
Web browsing is not consistent – Al news & features GPT offers real-time access to a manually curated news database about all minor and major features and changes on ChatGPT, Bard and Copilot (more apps coming soon!) 👇 pic.twitter.com/urtBRSVWDrMeet TestingCatalog GPT, AI news & features assistant! Web browsing is not consistent – Al news & features GPT offers real-time access to a manually curated news database about all minor and major features and changes on ChatGPT, Bard and Copilot (more apps coming soon!)
-
Revamped GPT for AI news and release tracking
By
–
I've pushed a complete revamp of this GPT to live! Now it works more consistently, offering a comprehensive deep dive into the newest releases and latest news. It will outperform news GPTs that rely on web browsing. Any feedback is welcome
-
Differences between MLOps, ModelOps, DataOps and AIOps
By
–
Defining the Differences between MLOps, ModelOps, DataOps & AIOps https://
bit.ly/42f1zP7 By @ingliguori @kenovy_it #AI #MachineLearning #MLOps -
Troubleshooting tip for custom GPT store development
By
–
TIP: In case you are trying to prepare your custom GPT for the store launch but #ChatGPT is broken > reload it with a disabled cache. @OpenAI team is actively updating it even during the weekend and at the same time there are loads of builders like you atm
-
RAGatouille LangChain Integration Simplifies Advanced Retrieval
By
–
Improved RAGatouille LangChain Integration We really enjoyed @bclavie
's new RAGatouille library. It makes advanced retrieval techniques (like ColBERT – more on that below) really easy to use We've worked on a tighter integration to make it *super simple* to use RAGatouille -
Unstructured Data Ingestion with LangChain.js Tutorial
By
–
Our friends at @UnstructuredIO are a great way to ingest unstructured data @devdigest recently made an awesome tutorial showing how to us them with LangChain.js. Shows how to do question-answering over third party data Check it out! https://
youtube.com/watch?v=2B161D
pvyxw
… -
Mixtral Offloading Repository Release and Documentation
By
–
Full repo: https://
github.com/dvmazur/mixtra
l-offloading/tree/master?tab=readme-ov-file
… -
Web Scraping Wikipedia Using LLM Agents Tutorial
By
–
How to Web Scrape Wikipedia with LLM Agents We this tutorial by Kenneth Leung. It shows how to take a CSV of entities and then use an agent to populate information about those entities by looking things up on Wikipedia Many real-world use cases! https://
medium.datadriveninvestor.com/how-to-web-scr
ape-wikipedia-using-llm-agents-f0dba8400692
…