I guess it thought OOP meant “clean” as in how do you dress the bird before you cook it. (As in: “clean a fish” means to filet a fish and prep it for cooking.)
But first it said they are usually clean. So that can’t be the context. If there was a context. But there is no context because AI is fucking stupid and all these c-suite assholes pushing it like their last bowel movement will be eating crow off of their golden parakeet about two years from now when all this nonsense finally goes away and the new shiny thing is flashing around.
There are signs of three distinct interpretations in the result:
On topic, the concept of cleaning a wild bird you are trying to save
Preparing a store bought Turkey (removing a label)
Preparing a wild bird that is caught
It's actually a pretty good illustration of how AI assembles "information shaped text" and how smooth it can look and yet how dumb it can be about it. Unfortunately advocates will just say "I can't get this specific thing wrong when I ask it or another LLM, so there's no problem", even as it gets other stuff wrong. It's weird as you better be able to second guess the result, meaning you can never be confident in an answer you didn't already know, but when that's the case, it's not that great for factual stuff.
For "doesn't matter" content, it may do fine (generated alternatives to stock photography, silly meme pictures, random prattle from background NPCs in a game), but for "stuff that matters", Generative AI is frequently more of a headache than a help.
It literally doesn't matter. When the most-used search engine on the planet automatically suggests these specific actions without you even clicking on a specific site? We're fucked. We had the chance to break up monopolies like Google, Microsoft and Facebook. We didn't take it...
This actually happens very frequently in the US. When hunters harvest a bird they report their kills in compliance with hunting regulations. If any of your birds have leg or neck bands you report that information as well. The bands have a tracking number on them, and scientists use them to monitor populations and migration patterns. It's literally part of their plan.
You get to keep the bands as well (I only have experience with banded geese and ducks). They're a neat memento.
I'm going to build a bunch of cyborgs, who follow orders exclusively via googleAI.
I figure once I release about 4 billion of them into the world, either google stops doing evil shit, or they do REALLY evil shit. We shall see what happens....
Fun time to remind everyone that pigeons aren't native to the Americas, and were brought over originally by the French primarily as a food source (although also as messengers; carrier pigeons).
The context is clear to a human. If an LLM is giving advice to everybody who asks a question in Google, it needs to do a much better job at giving responses.
Bought in a grocery store - see squab - they are usually clean and prepped for cooking. So while the de-boning instructions were not good, the AI wasn't technically wrong.
But while a human can make the same mistake and many here just assume the question was about how to wash a rescued pigeon - maybe that's not the original intent - what human can do that AI cannot is to ask for clarification to the original question and intent of the question. We do this kind of thing every day.
At the very best, AI can only supply multiple different answers if a poorly worded question is asked or it misunderstands something in the original question, (they seem to be very bad at even that or simply can't do it at all). And we would need to be able to choose the correct answer from several provided.
I mean, if they were actually "clean" and had a healthy diet compared to what they eat in urban areas, they could make an awesome protein source for the budget minded.
Though, you wouldn't want to eat one you "recovered" from an urban area that's had an unknown diet, due to all the toxins it may have accumulated in its body.
You theoretically could, but small birds like that have very little meat on their bones. Most hunt duck or turkey for a reason, the bigger birds have more meat.
Most people I know who hunt pigeons just take the breasts ("breasting pigeon") and bin the rest as it is not worth a hassle. Unlike turkey, you obviously need more than one pigeon for a meal unless you use it as a starter.
Google may not have enabled them in your region. Here in the UK they just appeared for me one day, a few months after I initially saw screenshots of them online. I didn’t do anything to enable them.
Or put every single word in quotations so it actually searches the whole string and doesn't truncate the query to just 2 or 3 keywords because this is clearly ignoring the "rescued" part.
Just did the same question. Answer given to me was vastly different:
Me:
How to clean a rescued pidgeon
ChatGPT:
Cleaning a rescued pigeon should be done carefully to avoid stressing or harming the bird. Here's a step-by-step guide to help you:
1. Assess the Pigeon's Condition
Check for injuries: If the pigeon is injured, weak, or sick, it's best to seek veterinary help before attempting to clean it.
Observe behavior: If the pigeon is acting stressed or aggressive, you may need to wait until it calms down.
2. Prepare the Cleaning Area
Warm water: Fill a basin or sink with lukewarm water, not hot or cold.
Mild soap: Use a gentle soap or baby shampoo without strong fragrances or chemicals.
Towels: Have clean towels ready for drying the pigeon afterward.
3. Handling the Pigeon Safely
Wear gloves: This can protect both you and the bird.
Secure hold: Hold the pigeon gently but firmly. Support its body with one hand and keep its wings close to its body to prevent flapping.
4. Cleaning the Pigeon
Partial cleaning: Focus on specific dirty areas rather than submerging the whole bird if possible.
Use a damp cloth: For lightly soiled areas, use a damp cloth or sponge to wipe the feathers gently.
Bath for heavier dirt: If a full wash is needed, place the pigeon in the water up to its chest. Avoid getting its head and neck wet unless absolutely necessary.
5. Rinsing
Rinse thoroughly: If you used soap, make sure to rinse all of it out of the feathers using clean, lukewarm water.
Avoid the face: Be careful not to get water in the pigeon’s eyes, nose, or ears.
6. Drying the Pigeon
Pat dry: Gently pat the pigeon with a towel to remove excess water. Avoid rubbing as it could damage the feathers.
Warm place: Keep the pigeon in a warm, draft-free area until it is completely dry. You can use a hairdryer on the lowest setting if the pigeon tolerates it, but keep it at a safe distance to avoid overheating.
7. Post-Cleaning Care
Observe behavior: Watch the pigeon for signs of stress or discomfort after the bath.
Provide food and water: Ensure the pigeon has access to fresh water and a safe, comfortable place to rest.
Additional Tips
Do not use strong disinfectants or chemicals that can harm the bird's sensitive skin and feathers.
Limit baths to when absolutely necessary, as frequent cleaning can strip the natural oils from the pigeon's feathers.
If the pigeon seems injured or unwell, contact a wildlife rescue center or avian veterinarian for guidance.
Looks like ChatGPT trained their models better, probably before sites could take measures to prevent that. Gemini however was thrown together by throwing money and people at the problem in order to catch up and not be left behind. Which from what I've read seems to be their biggest fear.
My Pixel 9 has AI everywhere but I certainly wouldn't pay the price they want to continue "using" Gemini after my trial.
Public free chatbots go up and down. Until recently I was finding Microsoft copilot to give the best answers. But they downgraded it recently, probably to much cost to keep it at that level, and now I'm finding openAI direct website to give best results... for now.
I just hope for a good enough self hosted model to be available before all the comercial ones shut up over a paywall/adwall for good (which is definitely coming sooner than later).
First off, the word "rescued" would have immediately made the context of "protect the pigeon" clear.
Second, a "rescued pigeon" wouldn't have a label on it, so it's clearly mixing in something from likely a store bought turkey, but then the other steps don't make sense either as those don't apply either.
A traditional search approach would not have made the mistake either. It would either have failed to find anything or found actual on topic results. It's "clever" enough to genericize "pigeon" to "birds" and hit upon text related to birds from a grocery store and birds that you hunted and mix all that together in a coherent language but with content that is nonsense.
In this case, hilarious, in other day to day situations, it's maddening, as some professional colleague gets the same sort of nonsense but lacks knowledge to correct it and relays it as fact. Then when called out on the data was in fact so bad it wasted time, they just say 'oh, lol, AI' (they wanted to take credit for it if it worked, but can hide behind AI when it doesn't).