Live data from Hacker News

GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

simonwillison.net

71–80 of 268 posts

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#73
post #43
post #18

That post definitely could have been 1/3rd the length

Yeah. I don't understand why the "Official name for the University of Cambridge" example is worth mentioning in the article.

It's an interesting and fun example?

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#74
post #17

[flagged]

This post is currently number 144 in newest and not listed in the second-chance pool https://news.ycombinator.com/pool so I think this is its first chance.

(This was posted before we merged the thread hither from https://news.ycombinator.com/item?id=45156067)

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#75

Earlier quoted context omitted.

> Please don't post shallow dismissals, especially of other people's work.

I asked why it's popping up over and over again in new today. I wouldn't have commented otherwise.

Reposts are allowed through after 8 hours if a story hasn't had significant attention yet. After that, we treat reposts as dupes for a year or so. This is in the FAQ: https://news.ycombinator.com/newsfaq.html.

This is on purpose, because we want good stories to get multiple chances at getting noticed. Otherwise there's too much randomness in what gets traction.

Plenty of past explanations here:

https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#76

These answers take a shockingly long time to resolve considering you can put the questions into Brave search and get basically the same answers in seconds.

The thing is, with Chat+Search you don't have to click various links, sift through content farms, or be subject to ads and/or accidental malware download.

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#77

Pretty wild! I wonder how much high school teachers and college professors are struggling with the inevitable usage though? "Do deep internet research and thinking to present as much evidence in favor of the idea that JRR Tolkein's Lord of the Rings trilogy was inspired by Mervyn Peake's Gormenghast series." https://chatgpt.com/share/68bcd796-bf8c-800c-ad7a-51387b1e53...

I was amused that it used the neologism 'steel-man' -- redundantly, too.

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#78
post #71

Is this the “Web Search”, “Deep Research”, or “Agent Mode” feature of ChatGPT? Navigating their feature set is… fun.

I have a feeling this is just ChatGPT 5 in thinking mode, with web search enabled at a profile level at least. Even without that, any indication for recent data or research and thinking will prompt it to think+research quite a bit, ie deep research.

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#79
I do miss the earlier "heavy" models that had encyclopedic knowledge vs the new "lighter" models that rely on web search. Relying on web search surfaces a shallow layer of knowledge (thanks to SEO and all the other challenges of ranking web results) vs having ingested / memorized basically the entirety of human written knowledge beyond what's typically reachable within the first 10 results of a web search (eg: digitized offline libraries).

Re: GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

#80

Pretty wild! I wonder how much high school teachers and college professors are struggling with the inevitable usage though? "Do deep internet research and thinking to present as much evidence in favor of the idea that JRR Tolkein's Lord of the Rings trilogy was inspired by Mervyn Peake's Gormenghast series." https://chatgpt.com/share/68bcd796-bf8c-800c-ad7a-51387b1e53...

Idea: workshops for teachers that teach them some kind of Socratic method that stimulates kids to support what they got from G with their own thinking, however basic and simple it may be.

Formulating the state of your current knowledge graph, that was just amplified by ChatGPT's research might be a way to offset the loss of XP ... XP that comes with grinding at whatever level kids currently find themselves ...

Post reply on HN