Mr. @QuinnyPig is right: using your local time zone for a database or server seems fine until it's not ("It's a one-way door that you don't realize you're passing through and then you spend decades unpacking the mess").
SYSTEMS
-
AI Model Accurately Detects Typing by Listening to Keystrokes
By
–
Incredible: This AI model can determine what you are typing just by listening to your keystrokes – with 95% accuracy:
-
AI Integration Reduces Human Trust and Coordination Efforts
By
–
"The introduction of automated players leads to a sharp increase in coordination failures between humans and AI, particularly in the short-term." Humans partnered with AI reported 1.44 std deviation lower trust & 0.81 SD lower effort. Implementing AI is not just a tech
-
MetaGPT: LLM-Based Multi-Agent Framework Encoding Human SOPs
By
–
5/ MetaGPT – a framework involving LLM-based multi-agents that encodes human standardized operating procedures (SOPs) to extend complex problem-solving capabilities that mimic efficient human workflows.
-
AI Infrastructure Setup: Key Elements and Success Metrics
By
–
Is your organization set up for #AI success? In this technical blog, discover the key elements, common mistakes, and metrics you need for a high-functioning AI infrastructure.
-
Smart Information Retrieval Strategies for AI Systems
By
–
The benefits over normal retrieval include: – You don't do retrieval if the question isn't about the topic
– You don't do retrieval if the question is about previously mentioned topics
– You can do multiple retrieval steps
– You can retrieve from multiple sources -
Seven Key Patterns for Building LLM-Based Systems
By
–
A very good blog post by @eugeneyan on “Patterns for building LLM based systems and products”. He covers the seven key patterns to build LLM based systems in greater detail. Link: https://
eugeneyan.com/writing/llm-pa
tterns/
… Must read for folks looking to build LLM based features / products -
Summary of LLM-based Systems Building Patterns
By
–
quick summary of @eugeneyan
's epic post on "Patterns for Building LLM-based Systems" -
AI Systems Becoming Incomprehensible: The Control Problem
By
–
The Coming Wave is producing new inventions that are increasingly beyond our ability to comprehend or control… Previously creators could explain how something worked, why it did what it did, even if this required vast detail. That’s increasingly no longer true. Many
-
Sparse models match dense accuracy with fewer flops
By
–
SPDF – Matching the downstream accuracy of a dense model with a sparse model using fewer flops – https://
hubs.li/Q01Z9v0G0