Feed aggregator

FizzBee: Open-source formal methods tool that's not hard

Hacker News - Mon, 04/01/2024 - 11:41am

Article URL: https://fizzbee.io/

Comments URL: https://news.ycombinator.com/item?id=39895359

Points: 1

# Comments: 1

Categories: Hacker News

Get Your Coffee Fix and Save Up to 47% Off These Keurig Machines - CNET

CNET Feed - Mon, 04/01/2024 - 11:02am
These coffee machines make it easier than ever to get your coffee fix and now you can get one with up to 47% off.
Categories: CNET

HelloFresh Is the Most Popular Meal Kit Service, but Is It the Best? We Tested It to Find out - CNET

CNET Feed - Mon, 04/01/2024 - 11:00am
HelloFresh offers easy meal kits, fair prices and more than 50 weekly recipes. We tried the popular meal kit service to see if it lives up to the hype.
Categories: CNET

Nab 20% Off Select Online Tax Prep Products From H&R Block - CNET

CNET Feed - Mon, 04/01/2024 - 10:52am
It's crunch time if you still need to file your taxes, but this offer can help you hold onto more of your money.
Categories: CNET

Structured Outputs with DSPy

Hacker News - Mon, 04/01/2024 - 10:49am

Unfortunately, Large Language Models will not consistently follow the instructions that you give them. This is a massive problem when you are building AI systems that require a particular type of output from the previous step to feed into the next one! For example, imagine you are building a blog post writing system that first takes a question and retrieved context to output a list of topics. These topics have to be formatted in a particular way, such as a comma-separated list or a JSON of Topic objects, such that the system can continue writing the blog post! I am SUPER excited to share the 4th video in my DSPy series, diving into 3 solutions to structuring outputs in DSPy programs: (1) TypedPredictors, (2) DSPy Assertions, and (3) Custom Guardrails with the DSPy programming model! TypedPredictors follow the line of thinking around JSON mode and using Pydantic BaseModels to interface types and custom objects into a JSON template for LLMs. The output can then be validated to provide a more structured retry prompt to correct the output structure! DSPy Assertions are one of the core building blocks of DSPy, offering an interface to input a boolean-valued function and a retry prompt which is templated alongside the past output to retry the call to the LLM! Custom Guardrails with the DSPy Programming Model are one of the things I love the most about DSPy — we have unlimited flexibility to control these systems however we want. The video will also show you how to write custom guardrails and retry Signatures and discussion around using TypedPredictors for your Custom Guardrails and potentially feeding your Custom Guardrails into a DSPy Assertion. I had so much fun exploring this topic! Further seeing how well OpenAI’s GPT-4 and GPT-3.5-Turbo, Cohere’s Command R, and Mistral 7B hosted with Ollama perform with each Structured Output strategy! I also found monitoring structured output retries to be another fantastic application of Arize Phoenix! I hope you find the video useful! Video: https://www.youtube.com/watch?v=tVw3CwrN5-8 If interested, all the code examples for this DSPy series can be found here! - https://github.com/weaviate/recipes

Comments URL: https://news.ycombinator.com/item?id=39894707

Points: 1

# Comments: 0

Categories: Hacker News

Calendaring and Scheduling Developer's Wiki

Hacker News - Mon, 04/01/2024 - 10:46am

Article URL: https://devguide.calconnect.org/

Comments URL: https://news.ycombinator.com/item?id=39894682

Points: 1

# Comments: 0

Categories: Hacker News

Pages