11–20 of 258 posts
Glad we didn't get to far into adopting something like Guardrails. This sort of kills it's main value prop for OpenAI. https://shreyar.github.io/guardrails/
In the openai blog post they mention "Convert “Who are my top ten customers this month?” to an internal API call" but I'm assuming they mean gpt will respond with structured json (we define via schema in function prompt) that we can use to more easily programatically make that api call? I could be confused but I'm interpreting this function calling as "a way to define structured input and selection of function and th…
After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary. As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical…
IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.
(except if the meaning is the JSON syntax is valid but may not conform to the schema, but they're unclear on that).
After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary. As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical…
IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.
After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary. As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical…
IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.
I know this should be able to be solvable by local LLMs and bert cosine similarity (it isn't exactly, but it's a start on the idea), but is there a way to do this with decoder models rather than encoder models with other logic?
In the openai blog post they mention "Convert “Who are my top ten customers this month?” to an internal API call" but I'm assuming they mean gpt will respond with structured json (we define via schema in function prompt) that we can use to more easily programatically make that api call? I could be confused but I'm interpreting this function calling as "a way to define structured input and selection of function and th…
This does not execute code!
Can I use this to make it reliably output code (say JavaScript)? I haven't managed to do it with just prompt engineering as it will still add explanations, apologies and do other unwanted things like splitting the code into two files as markdown.
Coincidentially, the new gpt-3.5-turbo-0613 model also has better system prompt guidance: for the demo above and some further prompt tweaking, it's possible to get ChatGPT to output code super reliably.
you can now trivially make GPT4 decide whether to call itself again, or to proceed to the next stage. it feels like the first XOR circuit from which we can compose a "transistor", from which we can compose a new kind of CPU.
After reading the docs for the new ChatGPT function calling yesterday, it's structured and/or typed data for GPT input or output that's the key feature of these new models. The ReAct flow of tool selection that it provides is secondary. As this post notes, you don't even need to the full flow of passing a function result back to the model: getting structured data from ChatGPT in itself has a lot of fun and practical…
IIRC, there's a way to "force" LLMs to output proper JSON by adding some logic to the top token selection. I.e. in the randomness function (which OpenAI calls temperature) you'd never choose a next token that results in broken JSON. The only reason it wouldn't would be if the output exceeds the token limit. I wonder if OpenAI is doing something like this.