Amazon Bedrock is a fully managed service that makes foundation models (FMs) from Amazon and leading AI companies available on AWS available through an API.
You have to sign in with a Google, Apple or Amazon account -
In the next step you can choose a username -
After I tried out some of the featured apps on the home page, I was able to build my own in minutes and publish it publicly - GeoFlix, check it out!
All I did was to provide the prompt that "the app should identify and suggest movies that prominently feature specified locations or place names within their storylines."
I edited the pre-created app name to GeoFlix and clicked on the "Make public and Share" button.
AWS is offering new PartyRock users a free trial without the need to provide a credit card or sign up for an AWS account for a limited time. The percentage balance reflecting the amount of free trial usage remaining for your account is displayed in real time within PartyRock on your Backstage profile page as PartyRock credit. PartyRock credit is calculated by your input tokens, output tokens, and generated images. PartyRock Credit usage varies by model to help users build intuition on cost consideration when using generative AI.
The relative consumption of each model is expressed in a scale of (1-3 token stacks) on the model selection dropdown. A (3 token stack) will consume the most credit, a (2 token stack) will consume moderate credit, and a (1 token stack) will consume the least credit.
While the free trial usage limit seems liberal, you have to be watchful of your consumption quota, which model you use and how may tokens are used while interacting with your apps or those created by others.
With some prompting, the Claude model also generated this description for the app -
Discover the magic of movie locations with GeoFlix. Our innovative app allows you to explore the world through the lens of cinema by identifying films that prominently feature real-world places. Just search for a city, country, or other geographic location, and GeoFlix will suggest relevant titles and provide fascinating details about how the setting is used in each movie's narrative. Whether you're planning a trip, studying a region, or just want to be transported somewhere new, GeoFlix makes it easy to find films that authentically showcase destinations worldwide.
PartyRock is indeed a great way to experiment with prompt engineering techniques, review generated responses, and develop an intuition for generative AI while creating and exploring fun apps!
Check this YouTube video if you need help in getting started with building your own app
Nikita Namjoshi 's video " How do thinking and reasoning models work? " from the Google for Developers channel explains the concepts behind "thinking models" or "reasoning models," such as Gemini, and how they use more computation at inference time to achieve better results in complex tasks. Video Summary The video focuses on how Large Language Models (LLMs) can be improved to handle complex tasks like coding, advanced mathematics, and data analysis by utilizing more compute power during the generation phase (inference or test time). The Problem: LLMs generate responses by predicting one token at a time. When solving complex problems, the model has to figure out the entire solution in a single pass to generate the correct final answer, which is difficult. The Solution: Chain of Thought (CoT): CoT prompting is a technique where the model is prompted to generate a series of intermediate steps (a "chain of thought") that lead to the final answer...
Kai-Fu Lee, Chairman of Sinovation Ventures and author of AI Superpowers and AI 2041: Ten Visions for Our Future on the China-US AI Race Q: There's still a lot of challenges when it comes to the whole monetization of AI, according to his perspective. In the last three years, though, how have you looked at this whole evolution of China AI versus the US, and what are the advantages and challenges for China? A: Yeah, so firstly, I disagree on the prospects for the USA. USA because yes, you look at OpenAI, it's making half billion spending 40 billion. It looks like a bad balance sheet, but most of that 40 billion is spent for future revenues. And if you believe there are 2x, 3x, 5x growth for the next three years, it's going to justify that valuation at some point. The bubble is merely that it's gotten ahead of itself, not the likelihood of growth in the future. Not saying it's worth its price, right, but there's absolute substance under the thumb. Now back to t...
This Week I Learned - * Rishikesh Sreehari has created NPSNAV.in website that hosts India's NPS Fund Database & API. You can access the latest NPS NAV and complete historical data for free. You can use the API programmatically or integrate live fund values into Google Sheets, Excel, or other tools. I needed an easy way to check the 52-week high and low of some schemes, so I vibe-coded a sample using the NPSNAV.in API which can be re-used for any NPS scheme. * Similarly, I used the free MFAPI.in API by Yuvaraj Loganathan to visualize the multi‑year NAV history of any Indian mutual fund scheme. The code sample shows seasonal patterns and the 52‑week high/low levels for any MF scheme at a glance. * These ChatGPT prompts can help you learn a new language. * Nitter.net is an open-source alternative Twitter front-end * Invidious is an open source alternative front-end to YouTube * Adafruit IO is a cloud service by Adafru...
Comments
Post a Comment