Live data from Hacker News

Launch HN: Needl (YC S22) – Simple search across all your apps

news.ycombinator.com

61–70 of 82 posts

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#61

How do you compre to https://slapdash.com ?

Biggest difference is search quality. Our entire product is focused on making information more accessible across web apps. We have generative Q&A search and semantic search, something Slapdash does not offer (to my understanding).

On the other side, we also don't offer the Command Bar-esque features that Slapdash and Raycast offer. For now, our #1 focus is search and search alone.

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#62

What does the prompt injection look like, how do you prevent hallucination

We've experimented with this a fair bit, very low occurrence of the model making up facts when the answer exists within a document, but users have reported outside information (general knowledge) being shown in their results. We essentially just prompt GPT-3 to ignore everything that is outside of the chunks of information we provide it.

Are there plans to back up the "suggested answer", which I presume is LLM generated, by a definitive source? The first question in the demo returned the relevant document you were looking for, but I didn't see this in the search results for the second question.

I'm not sure I would trust a system like this unless I could click through and see the source of the answer I'm reading, and make sure that the LLM is referencing the correct email/document.

This seems to be a common growing pain in places where an AI model is expected to provide authoritative answers - I wonder if (at least in your case) it's possible to use a more traditional fuzzy search algorithm to attempt to find the source, based on the LLM's answer string.

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#65

Earlier quoted context omitted.

We've experimented with this a fair bit, very low occurrence of the model making up facts when the answer exists within a document, but users have reported outside information (general knowledge) being shown in their results. We essentially just prompt GPT-3 to ignore everything that is outside of the chunks of information we provide it.

Are there plans to back up the "suggested answer", which I presume is LLM generated, by a definitive source? The first question in the demo returned the relevant document you were looking for, but I didn't see this in the search results for the second question. I'm not sure I would trust a system like this unless I could click through and see the source of the answer I'm reading, and make sure that the LLM is referen…

Currently something we're working on with prompt engineering, but love your suggested approach. We'll definitely look into that more -- thanks for sharing.

For now, the search is always generated from the first 5 or so results. So you always have an idea of where it's coming from.

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#66
Good luck with this, looks good, and an interesting project from a tech creator perspective. Particularly like the reassuring notes about auditing etc being central.

Minor note - the link to try the web version doesn't work for me from the pricing section free option down the page. Chrome/Firefox Android mobile and desktop view. The main link at the top works fine.

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#67

Good luck with this, looks good, and an interesting project from a tech creator perspective. Particularly like the reassuring notes about auditing etc being central. Minor note - the link to try the web version doesn't work for me from the pricing section free option down the page. Chrome/Firefox Android mobile and desktop view. The main link at the top works fine.

Great catch -- will definitely fix. Thanks a lot

Re: Launch HN: Needl (YC S22) – Simple search across all your apps

#70
I really like this idea! I definitely think this product has some potential. A few quick questions:

1. Does this integrate with the filesystem (specifically with MacOS) or iCloud Drive? 2. Are there any future plans to integrate with iMessage? While perhaps less important to enterprises, I feel like this could be very useful for “prosumer” productivity tool users like myself. 3. Are there any future plans for a mobile app (specifically on iPhone).

I’m excited to try this product out. Congrats on your launch!!

Post reply on HN