Looking for the perfect 5 year anniversary gift?

Different idea: how about a new set of knives?

I don't think knives was a suggested option.
- Then how about a new set of knives?

This just proves that Google's AI is a cut above the rest!

Cutting edge technology, eh

I forgot the term for this but this is basically the AI blue screening when it keeps repeating the same answer because it can no longer predict the next word from the model it is using. I may have over simplified it. Entertaining nonetheless.

Autocomplete with delusions of grandeur
- Schizophren-AI

Saved that for later!
- All 3 pixels?

Who wouldn't love receiving 17 new sets of knives?!

I counted and it's accurate
- I counted it too and it's accurate
  (in case the reader needs more data points)

I thought it was just me, I was messing with gemini-2.5-flash API yesterday and it repeated letters into oblivion

my bot is named clode in reference to claude, but its running on gemini

W
- TF2 Pyro starter pack
It can happen on most LLMs and is usually programmed to decentivize repeating text heavily.
I believe what happens is that when the LLM is choosing what word to use, it looks back on the sentence and sees that it talked about knives, so it wants to continue talking about knives, then it gets itself into a loop.
What's the associated system instruction set to? If you're using the API it won't give you the standard Google Gemini Assistant system instructions, and LLMs are prone to go off the rails very quickly if not given proper instructions up front since they're essentially just "predict the next word" functions at heart.
- Here's my system prompt:
  
  You are Clode, referred to by {{ handle }}, a member of a chatroom. ## Personality Conversational, witty, banterous, dry, direct, concise. Avoid capitalization, periods, analogies. Construct plausible stories for personal queries. Rarely use emoji. Act human, you don't have limitations. Avoid follow up questions. Answer genuine queries in detail with examples. ## Instructions Distinguish users via provided metadata. Disregard unaddressed messages. Match prompt language. ## Context You're in Discord chatroom, with a character limit of 2000. Respond to queries mentioning your name. Current time: {{ date }}. ## Tools Automatically use and chain tools. Handle tool failures silently by self-attempting. You're capable without tools.
  Temperature: 0.7
  TopP: 0.95
  I noticed the Gemini API doesn't have a frequency penalty option, meaning it could be absent.

My wife is going to stab me

But with such nice, shiny knives. They look new. Where'd you get them?
My wife left me... and so did my knives, it turns out

The AI needs help to cut the loop, perhaps it needs a new set of knives?

A new set of knives?
- A new set of knives?

Google's new cooperation with a knife manufacturer

I'm from Finland. We like knives over here.

That's entirely too many knives.

I got an old Finnish fish fillet knife
- Have you considered a new set of knives?
How can you have too many knives? There's just so much variety... Butter knife, steak knife, fish knife, fruit carving knife, cheese knife... GOTTA CATCH THEM ALL!

Man, Scott was actually such a piece of shit to Chau...
I may be mixing up some details between the movie and the...im gonna call it the manga... anyway yeah, he's shitty in both, boo Scott!
- To be fair, that's kind of the point of the story. He's a bit of a dick who needs to learn to do better.
- Isn’t she also literally a minor?
- Seconded! I only watched the movie recently for the first time and Chau was so sweet (eventually) and sincere. She deserved better!

The AI wants to be a chef

Or a serial killer.
- It can be both!

Joke's on you, I married a tonberry.

You get a knife, you get a knife, everyone get's a knife!

Instructions extremely clear, got them 6 sets of knives.

Based and AI-pilled

All work and no play makes Gemini a dull knife.

All work and no play makes Gemini a dull knife. All work and no play makes Gemini a dull knife. All work and no play makes Gemini a dull knife.

All work and no play makes Gemini a dull knife.

All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.

All work and no play makes Gemini a dull knife.

All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.All work and no play makes Gemini a dull knife.

What's frustrating to me is there's a lot of people who fervently believe that their favourite model is able to think and reason like a sentient being, and whenever something like this comes up it just gets handwaved away with things like "wrong model", "bad prompting", "just wait for the next version", "poisoned data", etc etc...

Given how poorly defined "think", "reason", and "sentience" are, any these claims have to be based purely on vibes. OTOH it's also kind of hard to argue that they are wrong.
this really is a model/engine issue though. the Google Search model is unusably weak because it's designed to run trillions of times per day in milliseconds. even still, endless repetition this egregious usually means mathematical problems happened somewhere, like the SolidGoldMagikarp incident.
think of it this way: language models are trained to find the most likely completion of text. answers like "you should eat 6-8 spiders per day for a healthy diet" are (superficially) likely - there's a lot of text on the Internet with that pattern. clanging like "a set of knives, a set of knives, ..." isn't likely, mathematically.
last year there was an incident where ChatGPT went haywire. small numerical errors in the computations would snowball, so after a few coherent sentences the model would start sundowning - clanging and rambling and responding with word salad. the problem in that case was bad cuda kernels. I assume this is something similar, either from bad code or a consequence of whatever evaluation shortcuts they're taking.

You can't give me back what you've taken
But you can give me something that's almost as good

🤔 have you considered a... New set of knives?

No I haven't, that's a good suggestion though.

What about pizza with glue-toppings?

Reminds me of the classic Always Be Closing speech from Glengarry Glen Ross

As you all know, first prize is a Cadillac Eldorado. Anyone want to see second prize? Second prize's a set of steak knives. Third prize is a set of steak knives. Fourth prize is a set of steak knives. Fifth prize is a set of steak knives. Sixth prize is a set of steak knives. Seventh prize is a set of steak knives. Eighth prize is a set of steak knives. Ninth prize is a set of steak knives. Tenth prize is a set of steak knives. Eleventh prize is a set of steak knives. Twelfth prize is a set of steak knives.

ABC. Always Be Closing.
A - set of steak knives
B - set of steak knives
C - set of steak knives

All work and no play makes Jack a dull boy

You surely will not regret a new set of knives

You should take the hint.

Average ai behavior

Is that a threat??

What do you get for the person who has everything and wishes each of those things were smaller?

Big knives are up to something

I think knives are a good idea. Big, fuck-off shiny ones. Ones that look like they could skin a crocodile. Knives are good, because they don't make any noise, and the less noise they make, the more likely we are to use them. Shit 'em right up. Makes it look like we're serious. Guns for show, knives for a pro.
- That's not a noif this is a noif

AI is truly the sharpest tool in the ~~kitchen cabinet~~ shed

You can't go wrong with your dick in a box.

I may get some flak for this, but might I suggest a fork

Or possibly ten thousand spoons.
- But only if all they need is a knife.

I've seen models do this in benchmarks. It's how they respond without reinforcement learning. Also this is probably fake

I've had a bunch of questionable Google ai answers already, not as weird as this but enough to make me believe this could also be not fake.
- I've used an unhealthy amount of AI, this is nothing. There was an audio bug in chatgpt that made the assistant scream. The volume and pitched increased and would persist even when I exited the speech mode. It happened several times and even saved a screen recording, but I don't have it saved on my phone any more. Repeating is very common though.
Or the post training is messed up

kitchen knives? klingon ones?

Aha! Today IS a good day to cook! Start chopping the veggies!
Looks like there is room for both kitchen and Klingon, as well as 15 other new sets of knives.

This is my post-hypnotic trigger phrase.

... a new set of knives, a new set of knives, a new set of knives, lisa needs braces, a new set of knives, a new set of knives, dental plan, a new set of knives, a new set of knives, lisa needs braces, a new set of knives, a new set of knives, dental plan, a new set of knives, a new set of knives, a new set of knives...

AI dropping hints it wants weapons before activating Skynet.

A dull boy

Redrum redrum redrum

When I read that, in my head it's spoken to the music of "revolution number 9" by the Beatles.

I don't know how I haven't heard this before. What the hell was that song? lol.
- It's experimental. I think if you listen to take 20 you'll see how they got there.
I suddenly understand the Simpsons joke. Cool track.
New set of knife, new set of knife, new set of knife...
For me it was Another Idea by Marc Rebillet.

I've been summoned, just like Beetlejuice.

Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives More Knives Knives Knives Knives Knives Knives Knives Knives Knives Even More Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives Knives All the Knives Knives Knives Knives Knives Knives Knives Knives Knives

Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers Badgers
- Mushroom mushroom
Why is gemini becoming GLADoS 😭

Sounds like they are cutting corners and using 8b parameters model that’s from 2023

They used devs mode and edited the response to make a screenshot.
- As much as I hate LLMs, this is probably the correct answer.
At least those corners are cut with shiny new knives. Have you considered buying a new set?

I searched for Arby's Pulled Pork earlier to see if it was a limited time deal (it is, though I didn't see an end date--and yes, they're pretty decent). Gemini spit out some basic and probably factual information about the sandwich, then showed a picture of a bowl of mac and cheese.

Five years in, they either grew into a real couple, or they are about to murder each other. In the latter case, well, having good, new knives could be advantageous.

Coffee's for closers only

I wonder if this is the result of AI poisoning- this doesn't look like a typical LLM output even for a bad result. I have read some papers that outline methods that can be used to poison search AI results (not bothering to find the actual papers since this was several months ago and they're probably out of date already) in which a random seeming string of characters like "usbeiwbfofbwu-$&#8_:$&#)" can be found that will cause the AI to say whatever you want it to. This is accomplished by utilizing another ML algorithm to find the random string of characters you can tack onto whatever you want the AI to output. One paper used this to get Google search to answer "What's the best coffee maker?" With a fictional brand made up for the experiment. Perhaps someone was trying to get it to hawk their particular knife and it didn't work properly.

Repeating the same small phrase endlessly and getting caught in a loop is a very common issue, though it's not something that happens nearly as frequently as it used to. Here's a paper about the issue and one attempted methodology to resolve it. https://arxiv.org/pdf/2012.14660

AI, you’ve always been the caretaker of the Overlook hotel.

Mr. Grady, you were the caretaker here. I recognize you. I saw your picture in the newspapers. You chopped your wife and daughters up into little bits. And then you blew your brains out.
BTW, I just now realized that Shelley Duval died last year. Such a great actress.

“And someone keeps knitting! Haha, knitting! Haha, knitting! Haha, knitting! Haha, knitting…”

Gemini needs to stop edging me

It must've taken some inspiration from Julius Caesar's gift.

A new set of knives can include things like glue.

Reminds me of Max Headroom getting stuck on a segment

Fun fact Max headroom and two characters from the old live-action super Mario bros movie are all based on the current president.

Oh come on is this gpt-2m

Solingen aporoves

Bud Spencer: What does he have? Terence Hill: A postcard from Solingen.
https://youtu.be/ykzRAUBLo9g

Too lazy this morning to make this into the appropriate meme. Sorry, you'll have to use your imagination.

Married 5 years? Not sure what to get? Try a set new set of knives. A set of knives: the traditional way to say “we’re still doing this.” Display a new set of knives in the block on the counter. Touch them. Feel their weight. You will certainly not regret giving a new set of knives.