ChatGPT Opened a New Era in Search. Microsoft Could Ruin It

https://www.wired.com/story/chatgpt-opened-a-new-era-in-search-microsoft-could-ruin-it/

by sharemywin • 3 years ago

35 22 3 years ago

PaulHoule3• 3 years ago

I think there's very little awareness of the use of cross-encoders for reranking

https://weaviate.io/blog/cross-encoders-as-reranker

but these are significant because they noticeably improve search ranking results and a development like that happens every 5-10 years or so. Getting a bunch of results from Bing and then reranking them with a cross-encoder is a low-hanging fruit in terms of making a better than status quo search engine.

kacperlukawski• 3 years ago

Yeah, that's correct. We also believe that's a good direction for improving search results quality and combining different methods of search: https://qdrant.tech/articles/hybrid-search/

PaulHoule3• 3 years ago

I like that article.

If the cross-encoder is well-calibrated then you really can merge search results from different sources the way IBM Watson did back in the day and not have to calibrate the individual sources.

james-revisoai2• 3 years ago

Yeah good to mention these. I think they may be slightly too slow running for now, as BERT was for Google search when first released, but one day these will help greatly.

PaulHoule3• 3 years ago

Cross-encoders are fine for reranking.

You're certainly not going to run them for every document in the collection but can you run them for the top N? I think the answer to that is yes.

freediver3• 3 years ago

This does not work that well because :

1) Re-ranking is only good as the results you originally get. If you get garbage in, you will likely get garbage out, no matter how you re-rank

2) Re-renking using semantic search does little to help with the main problem in search (SEO spam, low quality content). These 'bad' pages typically rank well in semantic search and re-ranking would probably just help boost them.

sharemywin• 3 years ago

If you want an alternative I've used these guys for stuff:

https://www.valueserp.com/

villgax• 3 years ago

More like MS-DOS, waiting on the Linux of LLMs

zeruch2• 3 years ago

Could?

zeruch2• 3 years ago

I like how I got downvoted, but looking at MSFTs moves the last few years show a company trying to deleverage its users privacy at any chance, and generally fumbling around like clumsy oafs trying to make new product that will have as much heft as its past OS and Office suites did.

stuckinhell• 3 years ago

Knowing microsoft has full access to source of GPT fills me with dread.

We need true open source alternatives asap.

jacooper4• 3 years ago

If only LLAMA had an actual open license...

As for alternatives, phind is pretty good and uses its own independent model, but it might be killed by this change, as AFAIK, they use bing for results.

jacooper4• 3 years ago

A search engine using Bing's index isn't a real competitor to google and bing.

A good example is something like Brave Search, Independent index with independent AI and its own AD network.

But this change really shows that Microsoft believes Bing can take on google now(and it does! BARD is absolute garbage compared to gpt-4), and it doesn't want anything or anyone getting in its way.

freediver3• 3 years ago

By this logic is Brave not a real competitor to Chrome?

jacooper4• 3 years ago

The difference is its not relying on licensing Chrome's code, rather its using the open chromium source code, which cab be used regardless if google wants it or not. That's why brave and edge can compete with chrome.

dclusin• 3 years ago

My personal prediction is that llm powered search will be as terrible as google search once people figure out how to game it. In a way probably worse because it will only give one answer instead of a list of answers that you can pick through.

rvz• 3 years ago

Exactly. An LLM-based search engine has already amounted into being a more untrustworthy search engine, even worse than Google, with hallucinated results and results that are just plain sophistry from the AI with a lack of reasoning and explanation.

The only 'killer' use-case for LLMs is 'summarization'. That is it.

jacooper4• 3 years ago

In my experience, bing accuracy mode and phind are very usable, certainly not perfect but mucht better than Bard.

t0mas88• 3 years ago

ChatGPT hallucinates a lot, but Bing chat so far for me doesn't do that. And it makes the key parts of the answer clickable to read the pages it got that from. So you can judge whether you trust that page or not.

Teever• 3 years ago

Maybe, but I feel like an LLM based search has one advantage over Google/Bing as they are today - you can host it locally and keep your searches private.

For non current events I'll take a locally run LLM over privacyless google even if the results aren't quite as good. Google knows this and they are scared.

ChatGPT Opened a New Era in Search. Microsoft Could Ruin It

Related Stories