Simon Willison’s Weblog

Subscribe

Series: Misconceptions about large language models

Large Language Models can behave in very unintuitive ways!

Atom feed

ChatGPT can’t access the internet, even though it really looks like it can

Visit ChatGPT can't access the internet, even though it really looks like it can

A really common misconception about ChatGPT is that it can access URLs. I’ve seen many different examples of people pasting in a URL and asking for a summary, or asking it to make use of the content on that page in some way.

[... 1678 words]

Don’t trust AI to talk accurately about itself: Bard wasn’t trained on Gmail

Visit Don't trust AI to talk accurately about itself: Bard wasn't trained on Gmail

Earlier this month I wrote about how ChatGPT can’t access the internet, even though it really looks like it can. Consider this part two in the series. Here’s another common and non-intuitive mistake people make when interacting with large language model AI systems: asking them questions about themselves.

[... 1950 words]

Think of language models like ChatGPT as a “calculator for words”

One of the most pervasive mistakes I see people using with large language model tools like ChatGPT is trying to use them as a search engine.

[... 1162 words]

We need to tell people ChatGPT will lie to them, not debate linguistics

ChatGPT lies to people. This is a serious bug that has so far resisted all attempts at a fix. We need to prioritize helping people understand this, not debating the most precise terminology to use to describe it.

[... 1174 words]

Lawyer cites fake cases invented by ChatGPT, judge is not amused

Visit Lawyer cites fake cases invented by ChatGPT, judge is not amused

Legal Twitter is having tremendous fun right now reviewing the latest documents from the case Mata v. Avianca, Inc. (1:22-cv-01461). Here’s a neat summary:

[... 2844 words]

ChatGPT should include inline tips

Visit ChatGPT should include inline tips

In OpenAI isn’t doing enough to make ChatGPT’s limitations clear James Vincent argues that OpenAI’s existing warnings about ChatGPT’s confounding ability to convincingly make stuff up are not effective.

[... 1488 words]

It’s infuriatingly hard to understand how closed models train on their input

One of the most common concerns I see about large language models regards their training data. People are worried that anything they say to ChatGPT could be memorized by it and spat out to other users. People are concerned that anything they store in a private repository on GitHub might be used as training data for future versions of Copilot.

[... 1465 words]

ChatGPT in “4o” mode is not running the new features yet

Visit ChatGPT in "4o" mode is not running the new features yet

Monday’s OpenAI announcement of their new GPT-4o model included some intriguing new features:

[... 865 words]

Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say

I’m beginning to suspect that one of the most common misconceptions about LLMs such as ChatGPT involves how “training” works.

[... 1543 words]