2 posts tagged with "context"

LLMs are forward thinkers, and that's a bit of a problem

December 19, 2023 · 12 min read

Ian Kelk

Developer Relations

This is going to be a weird post. And we're going to start with a thought experiment about a shark and an octopus.

A cartoon-style illustration, featuring a humorous underwater scene where a shark and an octopus are having an argument. The shark and octopus are depicted in a more exaggerated, cartoonish manner, with the shark sporting a grumpy expression and the octopus using its tentacles in a comedic, expressive way, as if in a lively debate. The underwater setting is whimsical, with stylized coral, seaweed, and playful small fish. The color palette is vibrant and lively, with brighter shades of blues, greens, and a touch of other colors, reflecting a more lighthearted and playful tone. The image maintains a 7:4 aspect ratio, offering a wide and engaging view of this charming and humorous underwater exchange. — Generated with OpenAI DALL-E 3 and edited by author.

Some key points I'll address here are:

Human brains are able to invent ideas without relying on a strictly linear train of thought.
LLMs like ChatGPT are autoregressive and are unable to continue a dialogue if they haven't already generated everything up to that point. This is because they don't "think" per se, but progressively generate a response using the parts of the response they previously created.
If you try to get an LLM to write text in the middle of a dialogue without previous context, it will give near-identical answers and attempt to conclude the conversation.
Prompting for "ridiculous" answers can spark creativity that helps break this pattern.
The reliance on a linear train of thought is a limitation for general intelligence. LLMs are ineffective if you ask them to generate the second part of a response without allowing them to generate the first part.

As I mentioned, this is going to sound a bit silly, but I promise there is a point!

How ChatGPT fools us into thinking we're having a conversation

November 26, 2023 · 9 min read

Ian Kelk

Developer Relations

Remember the first time you used ChatGPT and how amazed you were to find yourself having what appeared to be a full-on conversation with an artificial intelligence? While ChatGPT was (and still is) mind-blowing, it uses a few tricks to make things appear more familiar.

While the title of this article is a bit tongue-in-cheek, it isn't clickbait. ChatGPT does indeed use two notable hidden techniques to simulate human conversation, and the more you know about how they work, the more effectively you can use the technology.

A black and white illustration of a late-night talk show setting, titled 'The ChatGPT Show.' A classic, boxy robot with visible joints and a round head featuring antenna and eyes, is depicted as the guest. It's gesturing with its hands as if in conversation. The host, a man in a suit with neat hair and a professional demeanor, sits across from the robot at a curved desk. Microphones and notes are on the desk, with an urban skyline visible through the window in the background. — Generated with OpenAI DALL-E 3.

Some key points I'll address here are:

ChatGPT has no idea who you are and has no memory of talking to you at any point in the conversation.
It simulates conversations by "reading" the whole chat from the start each time.
As a conversation gets longer, ChatGPT starts removing pieces of the conversation from the start, creating a rolling window of context.
Because of this, very long chats will forget what was mentioned at the beginning.