Show HN: Test-driven development spreadsheet to track ChatGPT's failures - Klaput News

Show HN: Test-driven development spreadsheet to track ChatGPT's failures
2 by logicallee | 0 comments on Hacker News.
The recent discussion on "test-driven development"[1] made me want to track some of the most obvious failings I observe in ChatGPT. Here is my publicly viewable spreadsheet: https://ift.tt/iWPgEx0 You can add to it by completing the questions (just two are required, the prompt it got wrong and its wrong answer): https://ift.tt/E8SPi2J Feel free to list any other failures you've observed! [1] https://ift.tt/wp6uhE7

RELATED POST :
Memuat...

Comments

Post a Comment

Popular posts from this blog

Show HN: Modifying Clang for a Safer, More Explicit C++ - Klaput News

Show HN: Modifying Clang for a Safer, More Explicit C++ 15 by compiler-devel | 6 comments on Hacker News. Modified C++ Inspired by the paper "Some Were Meant for C" by Stephen Kell, I decided to show that it's possible to iterate C++ to be safer, more explicit, and less error-prone. Here's a possible starting point: I didn't invent a new language or compiler, but took the world's best compiler, clang, and modified it to begin iterating towards a new furture of C++. Naming things is hard, so I call this 'Modified C++'. Some of the following could be implemented as tooling in a linter or checker, but the idea is to update the compiler directly. I also wanted to learn more about clang. This compiler needs a flag to enable/disable this functionality so that existing library code can be used with a 'diagnostic ignored' pragma. You can build clang using the normal non-bootstrap process and you'll be left with a clang that compiles C++ but with...
Read more

Show HN: A tool to design and run user state machines - Klaput News

Show HN: A tool to design and run user state machines 5 by joemckenney | 0 comments on Hacker News. Hi everyone, I’m Joe, CTO at Dopt. We’re building a tool that lets you design user state machines with an SDK so that you can run them in your product. We offer a React SDK that lets you create instances of those machines for any user of your product and exposes methods for transitioning the state of the user—effectively moving them through the machine. Dopt then acts as a persistence layer for the users’ machine state. We call our machines “flows”. Dopt lets you send in data about your users (identify calls/properties) and lets non-devs define rules based on that data for which users should enter the flows. Non-devs can also update content and other custom properties that can be referenced via the SDK. For example, with Dopt’s SDK you can build: - a multi-step, interactive product walkthrough that helps users learn how to use a product by using it ( https://ift.tt/1TmNsig ) -a gettin...
Read more