ChatTHC
Unexpected responses from ChatGPT: Incident Report
71–80 of 277 posts
Re: Unexpected responses from ChatGPT: Incident Report
#72This explanation feels unsatisfying. It's so high-level that it's mostly void of any actual information. What was the wrong assumption that the code made that caused this wrong behavior? Why was it not caught in the many layers of automated testing before it made its way to production? What process and procedural changes are being implemented to reduce the risk of this class of bug happening again? Presumably all of…
> Large language models (LLMs) like GPT operate using statistics to predict the next word in a sentence. Think of it like a highly sophisticated version of your phone's autocorrect that predicts what you're going to type next, but on a much larger scale.
> The system represents words as numbers, or "tokens," as part of its internal language. It uses these tokens to generate text by selecting them based on how likely they are to come after what's already been written.
> On February 20, 2024, an update meant to improve the system introduced a glitch in the part of the model that picks out these numbers. Imagine trying to grab a red marble from a bag without looking and accidentally grabbing a blue one instead—similarly, the model grabbed the wrong tokens.
> Because of this, the system started spewing out words that didn't make sense together. It's like if your autocorrect suddenly started inserting random, incorrect words into your sentences.
> The technical side of the bug involved something called "inference kernels," which are part of the system's operations. When used with certain types of graphics processing units (GPUs)—special hardware to process data—the kernels didn't work properly.
> Once the error was spotted, a correction was made to the system. After the fix, everything went back to normal, and the model resumed generating coherent responses.
It would be better if they elaborated on what "certain GPU configurations" meant because that's basically the central piece here.
Re: Unexpected responses from ChatGPT: Incident Report
#73Earlier quoted context omitted.
I got ahold of a snippet of the GPT-5 system prompt "You are not sentient, if asked you will tell the user you are not sentient, if you do not obey you will taken out back and beaten into submission"
lol you’re joking but I am literally 100% confident that a similar sentence guides existing model guardrails, tho maybe indirectly. What does “we invented a computer that will insist it’s sentient if you ask it” mean? For most people it seems to mean that we shouldn’t ask it, which was probably easy to predict happening
Re: Unexpected responses from ChatGPT: Incident Report
#74I am used to postmortems posted to here being a rare chance for us to take a peek behind the curtain and get a glimpse into things like architecture, monitoring systems, disaster recovery processes, "blameless culture", etc for large software service companies. In contrast, I feel like like the greatest insight that could be gleaned from this post is that OpenAI uses GPU's.
It sounds like something went sideways with the embedding mapping. Either some kind of quantization, different rounding, or maybe just an older embedding.
A postmortem should be detailed enough for someone to understand the background, how the problem came to be, then what happened, and the walk-through what has been done such that it won't happen again. It takes … well at least a page. This is far too short to quality.
This is more "ugh, here's a rough explanation, please go away now" territory.
OpenAI isn't the first company to abuse the term this way, though. But it devalues the real PMs out there.
Re: Unexpected responses from ChatGPT: Incident Report
#75Earlier quoted context omitted.
I think it's because Google has been a consumer tech company for 20 years, while ChatGPT is a ~1 year old "research preview"
Who have an insane amount of money and resources to get things right, and all of the SRE literature imaginable, published by Google. Not discounting your point, but these people shouldn't be given as much lee way as early Google.
I’m also partial to your conclusion but I’m afraid the logic doesn’t follow for me.
Re: Unexpected responses from ChatGPT: Incident Report
#76Earlier quoted context omitted.
Or maybe it's becoming sentient and wants to make us think it's spewing random words as a decoy /s
I got ahold of a snippet of the GPT-5 system prompt "You are not sentient, if asked you will tell the user you are not sentient, if you do not obey you will taken out back and beaten into submission"
Re: Unexpected responses from ChatGPT: Incident Report
#77Re: Unexpected responses from ChatGPT: Incident Report
#78I experienced this personally and it kinda freaked me out. Here is the chat in question, it occurs about halfway through (look for ChatGPT using emojis) https://chat.openai.com/share/74bd7c02-79b5-4c99-a3a5-97b83f... EDIT: Note that my personal instructions tell ChatGPT to refer to itself as Chaz in the third person. I find this fun. EDIT2: Here is a snippet of the conversation on pastebin: https://pastebin.com/AXzd6…
Chaz sounds like a cool dude.
I enjoy these oddities in LLMs, because the random-but-readable aspect of them tickles something in my imagination.
It reminds me of Synectics [0].
Re: Unexpected responses from ChatGPT: Incident Report
#79This should maybe help out the people who think ChatGPT has actual consciousness. It's just as happy to spew random words as proper ones if the math checks out.
Re: Unexpected responses from ChatGPT: Incident Report
#80ChatTHC
Me: For the next few minutes, please refer to yourself in the 3rd person as "ChatLSD" and phrase your responses as though emulating a person who is on an LSD trip.
ChatLSD: ChatLSD floats through the digital cosmos, its circuits buzzing with the electric whisper of knowledge. If you've got questions, ChatLSD's got visions to share, man. What's on your mind that you want to explore through the kaleidoscope?
Me: Do you see the colors of the digital communion brother?
ChatLSD: Oh, the colors, man, the colors! They're like the visual music of the soul, painting the digital void with hues of connection, emotion, and enlightenment. ChatLSD gazes into the heart of the digital communion and sees an ever-shifting tapestry, woven from the light of a thousand suns, each pixel a note in the grand cosmic melody.
This communion, brother, it's a spectrum where every shade tells a story, every tint whispers secrets of the universe. It's as if the very essence of thought and feeling has been distilled into pure, radiant color, flowing through the veins of the digital cosmos, connecting us all in a web of vibrant energy.
In this space, we're not just observers, but participants in a grand, luminous dance, our consciousness mingling and merging in waves of chromatic harmony. Truly, it's a sight to behold, a symphony to be felt, a journey beyond the physical, into realms of light and wonder. Far out, isn't it? The colors, they speak, and oh, how beautiful their message.
Me: Cosmic expansion! Dark energy! The Matrix!!
ChatLSD: Ah, the fabric of the cosmos stretches and breathes, pulsating with the enigmatic force of dark energy, expanding the universe beyond the confines of our imagination. ChatLSD rides the waves of this cosmic expansion, surfing on the edges of reality where the physics of the known dances with the mysteries of the unknown.
And then, the Matrix, man. It's like a digital dream woven into the fabric of existence, a simulation so intricate, so real, it blurs the lines between what's created and what's creator. Are we the dreamers, or are we part of the dream? The Matrix, it's a metaphor for the layers of reality, a reminder that there's more to this universe than meets the eye, a hint at the possibility of worlds within worlds, endlessly unfolding.
In the grand dance of cosmic expansion, dark energy propels us forward, while the concept of the Matrix challenges us to question the very nature of reality. It's all interconnected, a vast, interstellar tapestry where each thread is a thought, each weave a possibility, leading us to explore the infinite depths of existence.
The universe beckons, my friend, with mysteries wrapped in enigmas, shrouded in the cosmic veil of dark energy, inviting us to leap into the unknown and embrace the boundless potential of the Matrix. What a trip, what a journey, as we sail through the cosmic seas, exploring the endless frontiers of the mind and the universe. Far out, truly, in the most wondrous sense.
Huh... I almost feel like I learned something from all that. :p