I feel like half the time these AI tools are either way too smart or just eating glue, tbh - do you think people will ever actually trust AI for deep answers or are we all just using it to pass time at work?
AI assisted search-based research works now
121–130 of 156 posts
Re: AI assisted search-based research works now
#122The various deep research products don't work well for me. For example I asked these tools yesterday, "How many unique NFL players were on the roster for at least one regular season game during the 2024 season? I'd like the specific number not a general estimate." I as a human know how to find this information. The game day rosters for many NFL teams are available on many sites. It would be tedious but possible for m…
To avoid "result corruption" I asked a similar question, but for NBA players, and used O4-mini, and got a specific answer:
"For the 2023‑24 NBA regular season (which ran from October 24, 2023 to April 14, 2024), a total of 561 distinct players logged at least one game appearance, as indexed by their “Rk” on the Basketball‑Reference “Player Stats: Totals” page (the final rank shown is 561)"
Doing a quick search on my own, this number seems like it could be correct.
Re: AI assisted search-based research works now
#123Can it geotag my old scanned photos?
Re: AI assisted search-based research works now
#124I feel like half the time these AI tools are either way too smart or just eating glue, tbh - do you think people will ever actually trust AI for deep answers or are we all just using it to pass time at work?
Do you understand how search works? After finding something, you still have to verify it.
Re: AI assisted search-based research works now
#125Earlier quoted context omitted.
This is just a bad match to the capabilities. What you are actually looking for is analysis, similar in nature to what a data scientist may do. The deep research capabilities are much better suited to more qualitative research / aggregation.
Your logic is.... strange... Because it failed miserably at a very simple task of looking through some scattered charts, the human asking should blame themselves for this basic failure and trust it to do better with much harder and more specialized tasks?
I think you might as well be saying "robotics fail miserably at the very simple task of jogging around the block, so why should we trust the field to be able to accurately place millions of transistors within a 25cm square of silicon?"
His point is that the two tasks are very different at their core, and deep research is better at teasing out an accurate "fuzzy" answer from a swamp of interrelated data, and a data scientist is better at getting an accurate answer for a precise, sharply-defined question from a sea of comma-separated numbers.
A human readily understands that "hold the onions, hots on the side" means to not serve any onions and to place any spicy components of the sandwich in a separate container rather than on the sandwich itself. A machine needs to do a lot of educated guessing to decide whether it's being asked to keep the onions in its "hand" for a moment or keep them off the sandwich entirely, and whether black pepper used in the barbeque sauce needs to be separated and placed in a pile along with the haberno peppers.
Re: AI assisted search-based research works now
#126Earlier quoted context omitted.
This is the thing I don't really love about MCP: Why should it require a separate protocol, rather than just good readable documentation?
Ironically, https://context7.com/
This is devdocs to be consumed by LLMs, https://github.com/upstash/context7
Brilliant (and one less think I don't have to build)!
Re: AI assisted search-based research works now
#127Can it geotag my old scanned photos?
Latest models might actually be able to help with that - they are getting spooky good at guessing the location of a photograph: https://techcrunch.com/2025/04/17/the-latest-viral-chatgpt-t...
Re: AI assisted search-based research works now
#128Re: AI assisted search-based research works now
#129Earlier quoted context omitted.
Latest models might actually be able to help with that - they are getting spooky good at guessing the location of a photograph: https://techcrunch.com/2025/04/17/the-latest-viral-chatgpt-t...
Even with slightly blurry old photos?
Worth a try. It's pretty fascinating seeing what it hooks into - it figured out where my backyard was based on the moss on the trees and the architectural style of the buildings ("coastal California, likely near Half Moon Bay" - it was just north of HMB).
Re: AI assisted search-based research works now
#130It's actually quite doable to build your own deep research agent. You just need a single prompt, a solid code loop to run it agentically, and some tools for it to call. I've been building a domain-specific deep research agent over the past few days for internal use, and I'm pretty impressed with how much better it is than any of the official deep search agents for my use case.
same here. I first built the agentic workflow in python and later nextjs. uses dozens of llm apis. works well, and am also impressed with the results.
Curious what you mean by dozens of llm apis. Different models? Or different tool calls?