Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by bodhi_mind on Monday March 20, 2023 @01:57PM
(#35235734)
Yes, I’m curious how they’re handling sandboxing for this effectively untrusted code.
[ Parent
| on HN ]
Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by Nebyou on Monday March 20, 2023 @02:18PM
(#35236116)
Our transformations are executed in a staging database/schema before deployment. We also have versioning and backtesting capabilities. In addition, you will have complete visibility of the code we produce before and after deployment.
Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by nmachado on Monday March 20, 2023 @02:11PM
(#35235994)
Yep - we do not expose any sort of prompting. We use the LLM only at specific parts of the process, and the user has no access to it.
Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by tough on Monday March 20, 2023 @09:10PM
(#35241267)
Doesn't the user provide the input that's feed to that function calling the LLM tho? Prompt hacking is a bit like sql injection in my mind but we don't have ORM's yet
Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by nmachado on Tuesday March 21, 2023 @12:37AM
(#35242621)
This would be a concern if we are feeding the raw user input and feed it directly into an LLM. In our case, we are not simply a wrapper over an LLM.
There are multiple parsing and rule-based steps done to the input schemas - we extract specific pieces from the schemas and convert them to our internal format before feeding it our models. Thus, it mitigates such malicious behavior.
Re:Launch HN: Lume (YC W23) – Generate custom data integrati...
by tough on Wednesday March 22, 2023 @09:58PM
(#35269584)
Thanks for the answer, I just found out about kor on twitter and made me think back of this thread, sharing in case it's of your interest https://eyurtsev.github.io/kor/