Hacker News new | past | comments | ask | show | jobs | submit
toomuchtodo | on: Changes at Google DeepMind: Demis Hassabis from CEO to Chair, Jeff Dean departs
Someone deleted a reply to this comment “And where does ChatGPT get the data for those answers?” they wrote and I think the question is important: LLM chatbots can crawl the web just as well as Google.
greenavocado | parent | next
The answer is Exa
toomuchtodo | root | parent
Nah, just another startup that’ll get acquired or a similar fate. Building the capability is a superior option imho, if you’re at Anthropic or OpenAI scale. Cut out the middleman.
greenavocado | root | parent
They can't do it, which is why they acquire.
suncemoje | parent
Huh? But only if you give it a tool it can use - which brings you back to Google (or Bing)
toomuchtodo | root | parent
Anyone can leverage common crawl and/or run their own crawler, to do so isn’t novel.

https://commoncrawl.org/

suncemoje | root | parent
Sure, I was just pointing at the fact that the question "And where does ChatGPT get the data for those answers?" has a two-part answer:

1) training data (common crawl as one example web data source), and

2) live data optionally retrieved at runtime.

My comment was about 2), and that part runs via a search engine (Bing?), at least if you look at how ChatGPT does it.

toomuchtodo | root | parent
Indeed, but what is the difference between crawl data and model data but decay rate? Models are trained on previous crawl data, but if an LLM provider engages a search engine to get "live data," that data isn't live but previously crawled as well (and perhaps not yet integrated into models as crawl data).

So, why would you use Google as a tool or search target when you can, in some combination, go direct to the website (or whatever the target data endpoint is) yourself as an LLM provider to retrieve the most recent data or rely on your own "hot cache" of that data that was crawled recently but said data is not stale enough warranting a live web crawl to retrieve and present to the user or AI agent? Is this capability to perform retrieval from a data source in real time not similar to an AI agent?

Broadly speaking, I'm just spitballing on the concept of "You must use a search engine for an LLM to return 'live-ish' results" as I think we're directionally headed to where that isn't the case.