Live data from Hacker News

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

simonwillison.net

1–10 of 268 posts

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

#2
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...

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

#5

[flagged]

Simon's writing is consistently either highly practical, or extremely high quality, or both. What's your reference frame to call it "bad" - your own comments?

FWIW I take his writings with a hefty pinch of salt these days. It seems incredibly concentrated on OpenAI to the detriment of anything else. This was only cemented when he ended up appearing on some OpenAI marketing video.

This is fine. He is his own person and can write about whatever he wants and work with whoever he wants, but the days when I'd eagerly read his blog to get a finger of the pulse of all of the main developments in the main labs/models has passed, as he seems to only really cover OpenAI these days, and major events from non-OpenAI labs/models don't seem to even get a mention even if they're huge (e.g. nano banana).

That's fine. It's his blog. He can do what he wants. But to me personally he feels like an OpenAI mouthpiece now. But that's just my opinion.

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

#6

[flagged]

Simon's writing is consistently either highly practical, or extremely high quality, or both. What's your reference frame to call it "bad" - your own comments?

Spending thousands of words to essentially say "ChatGPT's search feature works pretty well now" with mundane examples like finding UK cake pop availability or identifying buildings from train windows. This has been done before by less capable models - it's just a rehash. Should we expect newer models getting worse? The breathless "Research Goblin" framing and detailed play-by-play of basic web searches feels like padding to make a now routine tool use seem revolutionary.

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

#8

Earlier quoted context omitted.

Simon's writing is consistently either highly practical, or extremely high quality, or both. What's your reference frame to call it "bad" - your own comments?

FWIW I take his writings with a hefty pinch of salt these days. It seems incredibly concentrated on OpenAI to the detriment of anything else. This was only cemented when he ended up appearing on some OpenAI marketing video. This is fine. He is his own person and can write about whatever he wants and work with whoever he wants, but the days when I'd eagerly read his blog to get a finger of the pulse of all of the main…

Never read his blog and I like the writing.

> he feels like an OpenAI mouthpiece now

That seems a little harsh. But, I felt the same about older blogs I used to read such as CodingHorror. They just aren’t for me anymore after diverging into other topics.

I really liked this article and the coining of the term “Research Goblin”. That is how I use it too sometimes. Which is also how I used to use Google.

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

#9

[flagged]

It’s a very interesting balance between ‘LLMs are unpredictable thus useless’ and ‘LLMs are an amazing revolution, next step on the ladder of human civilization’.

I find it informative that search works so well. I knew it works well, but this feels like step above whatever Gemini can do, which is my go to workhorse for chatbots.

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

#10

Slightly off topic but chatGPT’s refusal to visually identify people, including dead historical personalities, has been a big let down for me. I can paste in an image of JFK and it will refuse to tell me who it is.

same with google lens, I do understand the motivation / laws behind it but yes , it really is a let down.
Post reply on HN