FRESH

Hacker News

Launch HN: Plexe (YC X25) – Build production-grade ML models from prompts

85 points by vaibhavdubey97

by sinanuozdemir

2 subcomments

by pplonski86

2 subcomments

Amazing! Great work. Congratulations on launch.
Few questions: 1. Can it work with tabular data, images, text and audio? 2. Data preprocessing code is deployed with the model? 3. Have you tested use cases when ML model was not needed? For example, you can simply go with average. I'm curious if agent can propose not to use ML in such case. 4. Do you have agent for model interpretation? 5. Are you using generic LLM or have your own LLM tuned on ML tasks?

by brightstar18

1 subcomments

Product seems cool. But can you help me understand if what you are doing is different from the following: > you put a prompt > Plexe glorifies that prompt into a bigger prompt with more specific instructions (augmented by schema definitions, intent and whatnot) > plug it into the provided model/LLM > .predict() gives me the output (which was heavily guardrailed by the glorified prompt in the step 2)

by liqilin1567

1 subcomments

> Each agent focuses on its domain: data analysis, feature engineering, model selection, deployment, and so on
Sounds very practical in real-world use cases. I trained a ML model couple months ago, I think it's a good case to test this product.

by abhishekbasu

1 subcomments

Great product and congratulations on the launch. Who is the target user vs customer? On the surface, and I may be wrong here, this feels like a LLM layered on top of a typical AutoML structure eg: TPOT, Caret. Is that the correct mental model for a tool like this? And if so, do you see a similar problem that these tools faced in broader adoption at companies?

by tnt128

2 subcomments

In the demo, you didn’t show the process of cleaning and labeling data, does your product do that somehow, or do you still expect the user to provide that after connecting the data source.

by alansaber

1 subcomments

Problem space is very interesting. Sounds like most of the work will be the data handling which is an evergreen problem

by canada_dry

1 subcomments

The tool gave me advice and code to do what I asked... but when I used the "export analysis" it did NOT include the code. It was simply an overview.
It would be more useful for the export to have an option (or by default) to include everything from the session.

by ryanmerket

1 subcomments

by throwacct

1 subcomments

Interesting. Are you guys only charging for the model building using tokens or overall usage (model building, inferences, etc)?

by johnsillings

1 subcomments

very cool – I like how opinionated the product approach is vs. a bunch of disconnected tools for specialists to use (which seems more common for this space).

by lcnlvrz

1 subcomments

by oxml

1 subcomments