ICYMI: Anthropic Workbench now allows marking "ideal outputs" in the prompt evaluator. Users can mark outputs which fit their expectations in order to improve their prompts further.
TOOLS
-
Arcee AI SEC Model for Financial Data Analysis Agent
By
–
I haven't used one but you might find inspiration from @arcee_ai
's SEC model https://
blog.arcee.ai/introducing-th
e-ultimate-sec-data-chat-agent-revolutionizing-financial-insights/
… -
Replicate simplifies API management and saves development time
By
–
Replicate makes my life so much easier for API management, security, and efficiency that I don't think I'll replace it. It would take me about 5 days of development to set up my serverless and API management, and I don't want to invest that time just to "earn more" :).
-
Using ChatGPT to Apply the OODA Loop for Faster Decisions
By
–
4/ The OODA Loop Prompt: "ChatGPT, how can I apply the OODA Loop to make faster, more effective decisions in [Specific Situation/Market]?"
-
Mermaid JS vs Cytoscape: Interactivity Trade-offs Explained
By
–
this is mermaid js, which is easy to read but harder to add interactivity than cytoscape
-
LangChain Hiring Designer and Frontend Engineer for Agent UI/UX
By
–
we're thinking a lot about the right UI/UX for agents at @LangChainAI, and building out developer tools like LangGraph Studio (below) that push that boundary
— Harrison Chase (@hwchase17) 21 septembre 2024
we're hiring a designer and FE engineer to help drive forward those efforts, come work with us:https://t.co/Jo8bMBoyHn pic.twitter.com/wznaisbaDIwe're thinking a lot about the right UI/UX for agents at @langchain
, and building out developer tools like LangGraph Studio (below) that push that boundary we're hiring a designer and FE engineer to help drive forward those efforts, come work with us: https://
langchain.com/careers -
Best way to count r’s in strawberry using external tools
By
–
In practice the safest way to get an LLM to do counting or string operations is to use external tools, like Python. ChatGPT has Python built in, but for simple problems you need to ask it to use it. So, if you *must*, this is the best way to count the r's in "strawberry" is:
-
LLMs struggle counting tokens without Chain-of-Thought or tools
By
–
What I'm disputing is the specific, but I think common, misconception that of course any LLM could count *tokens* easily; it's just that tokenization makes letters unnecessarily hard. Without CoT or tools, LLMs are just bad at counting.
-
New ‘Autofocus’ feature improves Claude prompt window workflow
By
–
Every click matters 👀
— 🚨 AI News | TestingCatalog (@testingcatalog) 21 septembre 2024
A very minor "autofocus" feature for Claude power users.
Now, regardless of where your cursor is, if you start typing, the text will automatically be added to the prompt window. pic.twitter.com/VWQvNYCWXXEvery click matters A very minor "autofocus" feature for Claude power users. Now, regardless of where your cursor is, if you start typing, the text will automatically be added to the prompt window.