HtmlRAG HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
PROMPT ENGINEERING
-
Haiku vs Haiku 3.5: optimal fallback strategy for AI
By
–
I'm wondering if it's a good fallback – use Haiku, and if the output isn't good, use Haiku 3.5
-
Anthropic Adds Customizable Chat Styles
By
–
BREAKING 🚨: Anthropic is working on "Customized Styles" which users can create and apply to their conversations.
— 🚨 AI News | TestingCatalog (@testingcatalog) 5 novembre 2024
Style creation UI also supports file upload where users can upload content examples 🔥 pic.twitter.com/eIHsISWpmEBREAKING : Anthropic is working on "Customized Styles" which users can create and apply to their conversations. Style creation UI also supports file upload where users can upload content examples
-
Improved prompt optimization achieves perfect results
By
–
and yes, the improved prompt it came up with actually worked perfectly
-
AI Model Automatically Improves Its Own Prompt Generation
By
–
AI self-improvement is coming. I just had an experience where the model automatically improved it's own prompt. Our AI generates code and prompts automatically — without my prompting, the agent realized that the output of the first run wasn't good enough, so it came up with
-
Generate Synthetic Data to Fine-Tune SLMs Effectively
By
–
NEW Tutorial + Notebook: Beat #GPT4o with only 10 Rows of Data Lack of training data is the #1 blocker to fine-tuning a high-quality #SLM. Not anymore! Check out our latest deep dive tutorial to learn how to generate effective #synthetic datasets with only 10 sample data
-
Claude 3.5 Haiku: Speed and Intelligence for Long Context Tasks
By
–
This combo of speed+intelligence makes 3.5 Haiku a particularly good choice for long context tasks where the model needs to quickly ingest lots of info (e.g. a codebase/financial docs/etc) and provide high-quality outputs. Combined with prompt caching… you get the idea.
-
RouteLLM: Automatic Query Routing to Optimal LLM Models
By
–
With many LLMs available, it can be difficult to choose which is best for your task. RouteLLM automatically routes your query to the best LLM
— Abacus.AI (@abacusai) 4 novembre 2024
Leverage the best of o1, Sonnet 3.5, GPT-4o, and Gemini! pic.twitter.com/fYZyRyhwyTWith many LLMs available, it can be difficult to choose which is best for your task. RouteLLM automatically routes your query to the best LLM Leverage the best of o1, Sonnet 3.5, GPT-4o, and Gemini!