|
You are here |
www.cyberdemon.org | ||
| | | | |
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. | |
| | | | |
dmitrybrant.com
|
|
| | | | | Seeing the congressional hearing about UAPs was a fun diversion. I prefer to use the original name "UFO", because switching to "UAP" is clearly an attempt to dodge the stigma that "UFO" has accumulated, and I don't think "UAP" deserves to get away with it so easily. What's funny about the current UFO discourse is ... Continue reading Thoughts on UFOs | |
| | | | |
fastml.com
|
|
| | | | | Large language models (LLMs) can now generate text difficult to distinguish from human-written text. This means they can generate spam. Here's ... | |
| | | | |
whitep4nth3r.com
|
|
| | | Common buzzwords in 2022 are serverless functions and The Edge. But what is The Edge? What are Edge Functions? And why does it matter? | ||