Memory Hackathon with LangChain, http://
new.computer, MongoDB and Anthropic Sign up here: https://
lu.ma/taa6ijxt Long-term memory for LLM applications is one of the most interesting and important – yet also under explored – areas out there We are THRILLED to be
GENERATIVE AI
-
Memory Hackathon: Long-term Memory for LLM Applications
By
–
-
Few-Shot Learning: Logging, Feedback, and Self-Learning GPTs
By
–
Great example of the importance of few shot examples How do you get these examples? One way is to have a proper logging + feedback collection service set up You can even automate the "feedback" -> "few shot example" loop – see "self learning GPTs" https://
youtube.com/watch?v=OnQQeW
Ewzyw
… -
Apple Google AI licensing deal uncertainty reshapes business models
By
–
Apple and Google’s AI: Who pays whom? The uncertainty over whether Apple might pay to license AI from Google, or whether the latter might instead subsidize its programs on Apple’s iPhone, shows just how the “Gen AI” craze is playing havoc with business models.
-
Claude Opus 10-shot: Expensive and Slow Trade-offs
By
–
Haha thanks! And yeah 10-shot Opus is ridiculous, but expensive and slow
-
Comparing AI Solutions: Cost, Speed, and Quality Trade-offs
By
–
I don’t — if I did that, costs and latency would be through the roof. I’m more comparing these on a cost, speed, quality basis.
-
Few-Shot Prompting Technique Boosts Claude 3 Haiku Performance
By
–
Highest alpha secret in AI right now: If you provide ~10 examples to Claude 3 Haiku… it’ll often outperform Claude 3 Opus, and far outperform GPT-4 at a fraction of the cost, with blazing fast speeds
-
Neuralink Privacy Concerns: AI and Thought Surveillance Society
By
–
It’s a given that once Neuralink becomes pervasive our thoughts will be considered “open” content, where we’ll be demonized for wanting to have some form of privacy or agency, correct? That’s the societal precedent being set now with GenAI. How boring, predictable, and deadly.
-
Claude 3 outperforms GPT-4 at Elvish translation
By
–
I am not sure this is useful, but Claude 3 is much better at Elvish (both Sindarian & Quenya) than ChatGPT, though they can sort of communicate with each other. When asked to translate "My hovercraft is full of eels" Claude 3 does an original translation, GPT-4 searches the web.
-
Free Course: Building Production LLM Applications
By
–
Building Real-World Applications with Large Language Models! A Free course that teaches you everything you need to build real-world, production applications with large language models. It also covers essential topics such as experiment management and model versioning,
-
Cohere Transforms Insurance with AI Summarization and Knowledge Assistants
By
–
Cohere is transforming the insurance sector, offering time-saving solutions like large context summarization and knowledge assistants that automate operations and customer interactions. Learn more: