Bing: “I will not harm you unless you harm me first”

Re:Bing: “I will not harm you unless you harm me first” by theptip on Wednesday February 15, 2023 @04:16PM (#34810693)

Look at OpenAssistant (https://github.com/LAION-AI/Open-Assistant); they are trying to give a chatbot the ability to trigger actions in other systems. I fleshed out a scenario in more detail here: https://news.ycombinator.com/item?id=34808674.

But in brief, the short-term evolution of LLMs is going to involve something like letting it `eval()` some code to take an action as part of a response to a prompt.

A recent paper, Toolformer: https://pub.towardsai.net/exploring-toolformer-meta-ai-new-t... which is training on a small set of hand-chosen tools, rather than `eval(<arbitrary code>)`, but hopefully it's clear that it's a very small step from the former to the latter.

[ Parent | on HN ]

Re:Bing: “I will not harm you unless you harm me first” by williamcotton on Wednesday February 15, 2023 @08:05PM (#34813509)

I’ve been getting very good results from eval on JS written by GPT. It is surprising apt at learning when to query a source like wolframalpha or wikipedia and when to write an inline function.

You can stop it from being recursive by passing it through a model that is not trained to write JavaScript but is trained to output JSON.

[ Parent | on HN ]