Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI assisted search-based research works now

simonwillison.net

Post reply on HN
Print view View original

21–30 of 156 posts

Re: AI assisted search-based research works now

#21

Post by skydhash »

simonw wrote: post #2

I think it's important to keep tabs on things that LLM systems fail at (or don't do well enough on) and try to notice when their performance rises above that bar. Gemini 2.5 Pro and o3/o4-mini seem to have crossed a threshold for a bunch of things (at least for me) in the last few weeks. Tasteful, effective use of the search tool for o3/o4-mini is one of those. Being able to "reason" effectively over long context inp…

One issue I can find with this workflow is tunnel vision, making ill informed decision because of the lack of surrounding information. I often skim books because even if I don't retain the content, I can have a mental map that can help me find further information when I need them. I wouldn't try to construct a complete answer to a question with just this amount of information, but I will use that map to quickly locate the source and have more information to synthesize the answer.

One could use the above workflow in the same way and argues that natural language search is more intuitive than keyword based search. But I don't think that brings any meaningful productivity improvement.

> Being able to "reason" effectively over long context inputs (particularly useful for understanding and debugging larger volumes of code) is another.

Any time I saw this "wish" pop up, my suggestion is to try a disassembler to reverse engineer some binary to really understand the problem of coming up with a theory of a program (based on Naur's definition). Individual statements are always clear (programming language are formal and have no ambiguity). The issue is grouping them, unambiguously define the semantic of these groups, and find the links between them, recursively.

Once that's done, what you'll have is a domain. And you could have skipped the whole thing by just learning the domain from a domain expert. So the only reason to do this is because the code doesn't really implement the domain (bugs) or it's hidden purposefully. So the most productive workflow there is to learn the domain first to find discrepancy (first case) or focus yourself on the missing part (second case). In the first case, the easiest approach is writing tests, and the more complete one is to do a formal verification of the software.

Re: AI assisted search-based research works now

#22

Post by loufe »

energy123 wrote: post #19

> The user-facing Google Gemini app can search too, but it doesn’t show me what it’s searching for. Gemini 2.5 Pro is also capable of search as part of its chain of thought but it needs light prodding to show URLs, but it'll do so and is good at it. Unrelated point, but I'm going to keep saying this anywhere Google engineers may be reading, the main problem with Gemini is their horrendous web app riddled with 5 annoy…

There must be some form of memory leak in AI Studio as I'll have to close and open a new tab after about 2 hours as it slowly grinds my slower computers to a halt. Its ability to create a markdown file without escaping the markdown itself (included code snippets) is definitely my first suggestion for them to fix.

It's a great tool, but sometimes frustrating.

Re: AI assisted search-based research works now

#23

Post by bluefirebrand »

simonw wrote: post #10
bluefirebrand wrote: post #6

Earlier quoted context omitted.

I don't think AI is trustworthy or accurate enough to be valuable for anyone trying to do real science That doesn't mean they won't try though. I think the replication crisis has illustrated how many researchers actually care about correctness versus just publishing papers

If you're a skilled researcher I expect you should be able to get great results out of unreliable AI assistants already. Scientists are meant to be good at verifying and double-checking results - similar to how journalists have to learn to derive the truth from unreliable sources. These are skills that turn out to be crucial when working with LLMs.

> Scientists are meant to be good at verifying and double-checking results

Verifying and double-checking results requires replicating experiments, doesn't it?

> similar to how journalists have to learn to derive the truth from unreliable sources

I think maybe you are giving journalists too much credit here, or you have a very low standard for "truth"

You cannot, no matter how good you are, derive truth from faulty data

Re: AI assisted search-based research works now

#24

Post by barbazoo »

simonw wrote: post #10
bluefirebrand wrote: post #6

Earlier quoted context omitted.

I don't think AI is trustworthy or accurate enough to be valuable for anyone trying to do real science That doesn't mean they won't try though. I think the replication crisis has illustrated how many researchers actually care about correctness versus just publishing papers

If you're a skilled researcher I expect you should be able to get great results out of unreliable AI assistants already. Scientists are meant to be good at verifying and double-checking results - similar to how journalists have to learn to derive the truth from unreliable sources. These are skills that turn out to be crucial when working with LLMs.

Same with using AI for coding. I can’t imagine someone having the expectation to use the LLM output verbatim but maybe I’m just not good enough at prompting.

Re: AI assisted search-based research works now

#25

Post by simonw »

bluefirebrand wrote: post #23
simonw wrote: post #10

Earlier quoted context omitted.

If you're a skilled researcher I expect you should be able to get great results out of unreliable AI assistants already. Scientists are meant to be good at verifying and double-checking results - similar to how journalists have to learn to derive the truth from unreliable sources. These are skills that turn out to be crucial when working with LLMs.

> Scientists are meant to be good at verifying and double-checking results Verifying and double-checking results requires replicating experiments, doesn't it? > similar to how journalists have to learn to derive the truth from unreliable sources I think maybe you are giving journalists too much credit here, or you have a very low standard for "truth" You cannot, no matter how good you are, derive truth from faulty da…

Don't make the mistake of assuming all journalists are the same. There's a big difference between an investigative reporter at a respected publication and someone who gets paid to write clickbait.

Figuring out that the data is faulty is part of research.

Re: AI assisted search-based research works now

#26

Post by simonw »

barbazoo wrote: post #24
simonw wrote: post #10

Earlier quoted context omitted.

If you're a skilled researcher I expect you should be able to get great results out of unreliable AI assistants already. Scientists are meant to be good at verifying and double-checking results - similar to how journalists have to learn to derive the truth from unreliable sources. These are skills that turn out to be crucial when working with LLMs.

Same with using AI for coding. I can’t imagine someone having the expectation to use the LLM output verbatim but maybe I’m just not good enough at prompting.

Using AI for coding effectively involves getting very good at testing (both manual and automated) and code review: https://simonwillison.net/2025/Mar/2/hallucinations-in-code/...

Re: AI assisted search-based research works now

#27

Post by throwup238 »

baq wrote: post #18

> I can feel my usage of Google search taking a nosedive already. Conveniently Gemini is the best frontier model for everything else, they’re very interested and well positioned (if not best?) to also be the best in deep research. Let’s check back in 3-6 months.

IMO they’re already the best. Not only is the rate limit much higher (20/day instead of OpenAI’s 10/month) but Gemini is capable of looking at far more sources, on the order of 10x.

I just had a research report last night that looked at 400 sources when I asked it to help identify a first edition Origin of Species (it did a great job too, correctly explaining how to identify a true first edition from chimeral ones).

Re: AI assisted search-based research works now

#28

Post by bluefirebrand »

simonw wrote: post #25
bluefirebrand wrote: post #23

Earlier quoted context omitted.

> Scientists are meant to be good at verifying and double-checking results Verifying and double-checking results requires replicating experiments, doesn't it? > similar to how journalists have to learn to derive the truth from unreliable sources I think maybe you are giving journalists too much credit here, or you have a very low standard for "truth" You cannot, no matter how good you are, derive truth from faulty da…

Don't make the mistake of assuming all journalists are the same. There's a big difference between an investigative reporter at a respected publication and someone who gets paid to write clickbait. Figuring out that the data is faulty is part of research.

Figuring out that data is faulty is one thing

There is still no possible way that a journalist can arrive at correct information, no matter how good, if they only have faulty data to go with

Re: AI assisted search-based research works now

#29

Post by bluefirebrand »

simonw wrote: post #26
barbazoo wrote: post #24

Earlier quoted context omitted.

Same with using AI for coding. I can’t imagine someone having the expectation to use the LLM output verbatim but maybe I’m just not good enough at prompting.

Using AI for coding effectively involves getting very good at testing (both manual and automated) and code review: https://simonwillison.net/2025/Mar/2/hallucinations-in-code/...

Manual testing, automated testing, and code review

All three of those things are things that software engineers rather reliably are bad at and cut corners on, because they are the least engaging and least interesting part of the job of building software

Re: AI assisted search-based research works now

#30

Post by simonw »

bluefirebrand wrote: post #28
simonw wrote: post #25

Earlier quoted context omitted.

Don't make the mistake of assuming all journalists are the same. There's a big difference between an investigative reporter at a respected publication and someone who gets paid to write clickbait. Figuring out that the data is faulty is part of research.

Figuring out that data is faulty is one thing There is still no possible way that a journalist can arrive at correct information, no matter how good, if they only have faulty data to go with

That's what (good) journalism is: the craft of hunting down sources of information, figuring out how accurate and reliable they are and piecing tougher as close to the truth as you can get.

A friend of mine is an investigative reporter for a major publication. They once told me that an effective trick for figuring out what's happening in a political story is to play different sources off against each other - tell one source snippets of information you've got from another source to see if they'll rebut or support it, or if they'll leak you a new detail because what you've got already makes them look bad.

Obviously these sources are all inherently biased and flawed! They'll lie to you because they have an agenda. Your job is to figure out that agenda and figure out which bits are true.

The best way to confirm a fact is to hear about it from multiple sources who don't know who else you are talking to.

That's part of how the human intelligence side of journalism works. This is why I think journalists are particularly well suited to dealing with LLMs - human sources lie and mislead and hallucinate to them all the time already. They know how to get (as close as possible) to the truth.

Post reply on HN