PSA It’s a new era of ergonomics.
The primary audience of your thing (product, service, library, …) is now an LLM, not a human. LLMs don’t like to navigate, they like to scrape.
LLMs don’t like to see, they like to read.
LLMs don’t like to click, they like to curl. Etc etc.
LLMS
-
LLM-First Ergonomics: Rethinking Interface Design for AI
By
–
-
Documentation and Products Must Evolve for LLM Interaction
By
–
The docs also have to change in the content. Eg instead of instructing a person to go to some page and do this or that, they could show curl commands to run – actions that are a lot easier for an LLM to carry out. Products have to change to support these too. Eg adding a
-
ChatGPT conversation reveals fading role of knowledge cutoffs
By
–
I just got 10 questions deep in a chat with ChatGPT o3 on some finer points of MCP before it occurred to me it had never heard of MCP before our chat. Search is finally starting to work. In a few months nobody will know what a "knowledge cutoff date" even is.
-
Exclusive Lightning Pod on Sleep-Time Compute with Charles Packer
By
–
Exclusive lightning pod with @charlespacker and the rest of the Sleep-Time Compute authors! https://
youtu.be/1UTo511O3-U -
Caching reduces inference costs by 4x efficiency gains
By
–
yes, caching is 4x less expensive than regular inference
-
LLMs Train Better Writing Habits Through Low-Cost Iteration
By
–
I think people *might* operationalize better habits after LLMs train them that throwing away a paragraph is basically costless.
-
Gemini API context caching updates support 2.5 Pro Flash
By
–
Context caching updates in the Gemini API: – Added support for 2.0 Flash
– Added support for 2.5 Pro Preview
– Reduced min context size from 32K down to 4K Much more to come still, please send any feedback on the experience! -
Steal my prompt to solve any problem with multiple expert perspectives
By
–
Steal my prompt to solve any problem from multiple expert perspectives at once, giving you deeper insights than any single approach. ——————————–
MULTIPLE EXPERTS METHOD
——————————– # ADAPTIVE INTELLIGENCE NETWORK You are a
— -
RAG Model Enhancement Through Metadata Extraction and Embedding
By
–
Supercharge your RAG models! Our next live demo takes you through creating functions that extract, structure & tag metadata from documents, & how these insights can fine-tune your embedding model for top-tier performance. Sign up: https://
snorkel.ai/webinar/weekly
-demo-with-qa/
… #AI #RAG -
Manual Function Call Formatting and Parsing Requirements
By
–
You have to format/parse function calling yourself right?