I trained a model on memes from the internet, and made a prompt that tells the Duck to make memes and quack. To my surprise, the Duck began to insert himself into those memes. I cracked up for hours that first night. So far everyone who plays with the Duck a bit finds something
PROMPT ENGINEERING
-
Agent Builder Released with Weekly Custom Agent Workshops
By
–
We finally released our agent builder in the beginning of the year and have started having workshops every week showing people how to make custom agents.
— Gene Kogan (@genekogan) 23 janvier 2025
The Duck character was born out of this https://t.co/DYFT91ZqnsWe finally released our agent builder in the beginning of the year and have started having workshops every week showing people how to make custom agents. The Duck character was born out of this
-
Tiny AI Models Struggle with Coding Tasks Compared to Reasoning
By
–
It will be a while before tiny models can code well, programming needs much more mental horsepower than reasoning
-
Citations Feature Outperforms Custom Methods in Internal Evaluations
By
–
In our internal evals, we found Citations performance exceeds custom citation methods for generating accurate/consistent citations. It also requires significantly fewer tokens than having to implement your own citations prompt since Claude already knows the format to use.
-
Claude Citations Feature for PDFs and Text Documents
By
–
With Citations enabled, Claude can cite chunks of content from pdfs, plain text docs, and text chunks. The returned citations are easy to parse, and Claude makes sure to only highlight the part of the response that is applicable to the citation.
-
Anthropic API Citations Feature Now Available for Grounded Responses
By
–
We've rolled out Citations in the Anthropic API. Citations allows Claude to ground its answers in user-provided information and provide precise references to the sentences and passages used in its responses. Here's how it works:
-
ChatGPT vs Claude vs o1: Which AI tool works best?
By
–
For code? For writing I still find ChatGPT better. Claude’s ‘personality’ can be somewhat sanctimonious – o1 is much more willing to collaborate with me. What y’all use for your needs and what works best?
-
One-Prompt Consistent Text-to-Image Generation Method
By
–
3/3 Paper "One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt"
-
Write LLM Evaluations Like Software Tests
By
–
write LLM evals like you write software tests (pytest/vitest/jest)
— Harrison Chase (@hwchase17) 22 janvier 2025
writing software tests is standard practice. writing evals for LLMs is equally important, but we don't see it as common place yet
we hope this helps bridge the gap! https://t.co/GZozKNbOw0write LLM evals like you write software tests (pytest/vitest/jest) writing software tests is standard practice. writing evals for LLMs is equally important, but we don't see it as common place yet we hope this helps bridge the gap!
-
Building LLM Agents with Computer Use Capability
By
–
Our first short course with @AnthropicAI! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let… pic.twitter.com/ghG3uGcRuP
— Andrew Ng (@AndrewYNg) 22 janvier 2025Our first short course with @AnthropicAI
! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let