Great American humorist. C# developer. Open source enthusiast.

XMPP: wagesj45@chat.thebreadsticks.com
Mastodon: wagesj45@mastodon.jordanwages.com
Blog: jordanwages.com

  • 0 Posts
  • 17 Comments
Joined 2 years ago
cake
Cake day: June 12th, 2023

help-circle



  • who don’t know how to implement it

    He didn’t say anything about replacing them. Certain tedious aspects that get farmed out to junior devs the AI will certainly be able to do, especially under supervision of a developer. Junior devs that refuse to learn how to use and implement the AI probably will get left behind.

    AI won’t replace anyone for a long time (probably). What it will do is bring about a new paradigm on how we work, and people who don’t get on board will be left behind, like all the boomers that refuse to learn how to open PDF files, except it’ll happen much quicker than the analogue-to-digital transition did and the people effected will be younger.







  • Sometimes ChatGPT can be legitimately funny. I asked it to fill out the permissions application as Meta.

    A high step count might be rewarded with an ad for comfortable running shoes; prolonged inactivity could trigger promotions for ergonomic chairs.

    LOL


    Dear App Store Reviewer,

    We’re pleased to outline our reasons for the various permissions required by our Threads application.

    Permission #1: Location Access to location data allows us to provide a more personalized user experience. Localized content, such as debates about neighborhood parking restrictions, would facilitate more engaging interactions. It also enables more accurate restaurant ads.

    Permission #2: Health Data With health data, we can offer timely suggestions for wellness activities based on user habits. A high step count might be rewarded with an ad for comfortable running shoes; prolonged inactivity could trigger promotions for ergonomic chairs.

    Permission #3: Microphone Access Audio transcriptions serve to identify users’ conversation topics, allowing us to tailor content to their interests. Casual mentions of Italian cuisine could prompt an influx of pasta maker ads, enhancing their culinary explorations.

    Permission #4: Camera Access Camera access improves our ability to understand user preferences through their captured images. Frequent snapshots of their pet parrot might lead to a subtle increase in bird seed and cage cleaner advertisements.

    Permission #5: Contact List Contact lists assist us in identifying common interests within a user’s network. Frequent discussions about vintage car restoration with certain contacts might result in targeted ads for classic auto parts, supporting their hobby.

    Permission #6: Calendar Calendar sync provides us insight into users’ upcoming events, allowing for timely content suggestions. If a user’s calendar reveals a dental appointment, we might find it apt to provide ads for mouthwash and high-end toothbrushes.

    Permission #7: Biometric Data Biometric data offers enhanced user security, while also informing us about their stress levels. Irregular heartbeats during work hours might indicate a need for calming ads featuring spa retreats or meditation apps.

    Permission #8: Browsing History By understanding a user’s browsing habits, we can refine the content we present to them. Browsing for second-hand furniture might result in a myriad of ads for antique shops, aiding in their quest for the perfect vintage armoire.

    Permission #9: Social Media Account Linking Linking social media accounts allows us to understand a user’s broader digital footprint, leading to a comprehensive content curation strategy. Regular ‘likes’ on pictures of home-baked bread across platforms might trigger an increase in ads for artisanal bread making kits.

    Permission #10: Dream Journal Entries Our most innovative request, access to users’ dream journal entries, could provide a unique perspective on their subconscious interests. Dreams of tropical beaches could result in a range of ads for sun hats, SPF creams, and all-inclusive resort packages.

    We trust these explanations clarify our intent: providing a user-centric application experience, catered to individual lifestyles, with the necessary bonus of extremely personalized advertising.

    Yours sincerely, The Facebook Team



  • Posters aren’t saying that its impossible to put search results through an LLM and ask it to cite the source it reads. They’re saying that the neural networks, as used today in LLMs, do not store token attribution in the vocabulary or per node. You can implement a system for the neural network to work in that provides it the proper input (search results) and prodding (a prompt that encourages the network to biasing toward citation), not that the single LLM can conceptualize of that on its own.