|
You are here |
rrich.io | ||
| | | | |
isthisit.nz
|
|
| | | | | August 2024 Update: Now a solved problem. Use Structured Outputs. Large language models (LLMs) return unstructured output. When we prompt them they respond with one large string. This is fine for applications such as ChatGPT, but in others where we want the LLM to return structured data such as lists or key value pairs, a parseable response is needed. In Building A ChatGPT-enhanced Python REPL I used a technique to prompt the LLM to return output in a text format I could parse. | |
| | | | |
www.wired.com
|
|
| | | | | You can now publish a bespoke version of ChatGPT that you've trained yourself. The marketplace for these custom GPTs is open to the public and works in a way that's similar to Apple's App Store. | |
| | | | |
simonwillison.net
|
|
| | | | | The biggest announcement from last week's OpenAI DevDay (and there were a LOT of announcements) was GPTs. Users of ChatGPT Plus can now create their own, custom GPT chat bots ... | |
| | | | |
www.windowscentral.com
|
|
| | | Anthropic CEO Dario Amodei recently admitted that the company doesn't know precisely how AI works as it scales greater heights and becomes more advanced. | ||