> And I also found the basic tier of ChatGPT hallucinated my app's purpose in a way that was borderline slanderous.
I'm curious about this, what exactly did ChatGPT write and how was it borderline slanderous? Sounds like a big danger.
I'm curious about this, what exactly did ChatGPT write and how was it borderline slanderous? Sounds like a big danger.
It's not like the bad old days where sentiment analysis was a bag of words model, add up all the "positive" words and subtract from that total the number of "negative" words — back then, they would mis-identify e.g. "Product was not as described, it did not come with batteries, and the surface wasn't even painted" as "this review favours this product" because they couldn't handle "not" or "wasn't".
----
CurrentKey Stats is a macOS application designed to enhance your productivity by offering detailed insights into your app usage and providing advanced management of your Mac's virtual desktops, known as "Spaces."
Key Features:
Time Tracking: Unlike macOS's Screen Time, which tracks total app usage, CurrentKey Stats monitors the time each app spends in the foreground, offering a more accurate representation of active usage.
Room Management: The app allows you to assign custom names and unique menu bar icons to each Space, facilitating easy identification and navigation. You can switch between these "Rooms" using the menu bar icon or customizable hotkeys.
Automation Support: For advanced users, CurrentKey Stats supports AppleScript, enabling you to automate actions when entering or leaving specific Rooms. This feature can trigger scripts to perform tasks like launching applications, adjusting system settings, or controlling smart home devices.
Privacy-Focused: The application prioritizes user privacy by keeping all data local on your device, ensuring that your usage statistics are not shared externally.
By combining detailed app usage statistics with enhanced Space management and automation capabilities, CurrentKey Stats aims to help you use your Mac more efficiently and deliberately.
----
But more generally, I think people often look at LLMs and assume that the current flaws will be around forever and this will be horrible. But all technologies have big, obvious flaws when they're first introduced and these get fixed because there's a strong incentive to have a less bad product.
o1 says "I’m not aware of a widely recognized or universally known product called “CurrentKey Stats,” so it may not be a mainstream or highly publicized app. There are a few possibilities, though:" and then some guesses.
o3-mini is similar: "I couldn’t find any widely recognized information about an app specifically called CurrentKey Stats. It’s possible that:"
When I turn on its shiny new search capability, it correctly identifies and summarizes the app.
o3-mini-high, search turned off, asks for clarification.
Which means the default free 4o is quietly doing retrieval-augmented generation behind the scenes. I thought o3-mini would search if it didn't know the topic, but I might be misremembering.