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

Watching o3 guess a photo's location is surreal, dystopian and entertaining

simonwillison.net

Post reply on HN
Print view View original

391–400 of 453 posts

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#391

Post by edanm »

SamPatt wrote: post #144
simonw wrote: post #119

Earlier quoted context omitted.

I'd be fascinated to read more about this. I'd love to see a sample screenshot of a few of your cards too.

Sure, I'll write something up later. I'll give you two samples now. One reason I love the Obsidian + Markdown + Spaced Repetition plugin combo is how simple it is to make a card. This is all it takes: https://cdn.jsdelivr.net/gh/sampatt/media@main/posts/2025-04... The top image is a screenshot from a game, and the bottom image is another screenshot from the game when it showed me the proper location. All I need to do…

This is fascinating! Thanks for sharing.

Small question - have you ever used Anki, and/or considered using it instead of this? I am a long-time user of Anki but also started using Obsidian over the last few years, wondering if you ever considered an Obsidian-to-Anki solution or something (don't know if one even exists).

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#393

Post by the_duke »

coffeebeqn wrote: post #357
spaceman_2020 wrote: post #342

Earlier quoted context omitted.

This is also why I buy the apocalyptic headlines about AI replacing white collar labor - most white collar employment is mostly creating the same things (a CRUD app, a landing page, a business plan) with a few custom changes Not a lot of labor is actually engaged in creating novel things. The marketing plan for your small business is going to be the same as the marketing plan for every other small business with some…

I don’t know if most software engineers build toy CRUD apps all day? I have found the state of the art models to be almost completely useless in a real large codebase. Tried Claude and Gemini latest since the company provides them but they couldn’t even write tests that pass after over a day of trying

Agreed in general, the models are getting pretty good at dumping out new code, but for maintaining or augmenting existing code produces pretty bad results, except for short local autocomplete.

BUT it's noteworthy that how much context the models get makes a huge difference. Feeding in a lot of the existing code in the input improves the results significantly.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#394

Post by throwaway4aday »

kuboble wrote: post #373
AlexCoventry wrote: post #340

Earlier quoted context omitted.

Can you give an example? Have you tried it recently with the higher-end models?

I have asked chatgpt reasoning model to solve chess endgames where white had king and a queen vs king and a rook on a 7x8 chessboards. So to compute value for all positions and find the position which is the longest win for white. Not creative, not novel and not difficult algorithmic task. But it requires some reasoning, planning and precision. It failed miserably.

I think you need to be more specific about which "chatgpt reasoning model" you used. Even the free version of chatgpt has reasoning/thinking now but there are also o1-mini, o1, o1-pro, o3-mini, o3, and o4-mini and they all have very different capabilities.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#395

Post by HenryBemis »

brundolf wrote: post #199
fire_lake wrote: post #177

Earlier quoted context omitted.

Which also fits with how it performs at software engineering (in my experience). Great at boilerplate code, tests, simple tutorials, common puzzles but bad at novel and complex things.

Yep. But wonderful at aggregating details from twelve different man pages to write a shell script I didn't even know was possible to write using the system utils

Is it 'only' "aggregating details from twelve different man pages" or has it 'studied' (scraped) all (accessible) code in GitHub/GitLab/Stachexchange/etc. and any other publicly available coding repositories on the web (and for the case of MS the Git it owns)? Together with descriptions of what is right and what is wrong..

I use it for code, and I only do fine tuning. When I want something that is clearly never done before, I 'talk' to it and train it on which method to use, and for a human brain some suggestions/instructions are clearly obvious (use an Integer and not a Double, or use Color not Weight). So I do 'teach' it as well when I use it.

Now, I imagine that when 1 million people use LLMs to write code and fine tune it (the code), then we are inherently training the LLMs on how to write even better code.

So it's not just "..different man pages.." but "the finest coding brains (excluding mine) to tweak and train it".

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#396

Post by flir »

coffeebeqn wrote: post #357
spaceman_2020 wrote: post #342

Earlier quoted context omitted.

This is also why I buy the apocalyptic headlines about AI replacing white collar labor - most white collar employment is mostly creating the same things (a CRUD app, a landing page, a business plan) with a few custom changes Not a lot of labor is actually engaged in creating novel things. The marketing plan for your small business is going to be the same as the marketing plan for every other small business with some…

I don’t know if most software engineers build toy CRUD apps all day? I have found the state of the art models to be almost completely useless in a real large codebase. Tried Claude and Gemini latest since the company provides them but they couldn’t even write tests that pass after over a day of trying

Our current architectures are complex, mostly because of DRY and a natural human tendency to abstract things. But that's a decision, not a fundamental property of code. At core, most web stuff is "take it out of the database, put it on the screen. Accept it from the user, put it in the database."

If everything was written PHP3 style (add_item.php, delete_item.php, etc), with minimal includes, a chatbot might be rather good at managing that single page.

I'm saying code architected to take advantage of human skills, and code architected to take advantage of chatbot skills might be very different.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#397

Post by kypro »

coffeebeqn wrote: post #357
spaceman_2020 wrote: post #342

Earlier quoted context omitted.

This is also why I buy the apocalyptic headlines about AI replacing white collar labor - most white collar employment is mostly creating the same things (a CRUD app, a landing page, a business plan) with a few custom changes Not a lot of labor is actually engaged in creating novel things. The marketing plan for your small business is going to be the same as the marketing plan for every other small business with some…

I don’t know if most software engineers build toy CRUD apps all day? I have found the state of the art models to be almost completely useless in a real large codebase. Tried Claude and Gemini latest since the company provides them but they couldn’t even write tests that pass after over a day of trying

Most senior SWEs, no. But most technical people in software do a lot of what the parent commenter describes in my experience. At my last company there was a team of about 5 people whose job was just to make small design changes (HTML/CSS) to the website. Many technical people I've worked with over the years were focused on managing and configuring things in CMSs and CRMs which often require a bit of technical and coding experince. At the place I currently work we have a team of people writing simple python and node scripts for client integrations.

There's a lot of variety in technical work, with many modern technical jobs involving a bit of code, but not at the same complexity and novelty as the types of problems a senior SWE might be working on. HN is full of very senior SWEs. It's really no surprise people here still find LLMs to be lacking. Outside of HN I find people are far more impressed/worried by the amount of their job an LLM can do.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#398

Post by SamPatt »

edanm wrote: post #391
SamPatt wrote: post #144

Earlier quoted context omitted.

Sure, I'll write something up later. I'll give you two samples now. One reason I love the Obsidian + Markdown + Spaced Repetition plugin combo is how simple it is to make a card. This is all it takes: https://cdn.jsdelivr.net/gh/sampatt/media@main/posts/2025-04... The top image is a screenshot from a game, and the bottom image is another screenshot from the game when it showed me the proper location. All I need to do…

This is fascinating! Thanks for sharing. Small question - have you ever used Anki, and/or considered using it instead of this? I am a long-time user of Anki but also started using Obsidian over the last few years, wondering if you ever considered an Obsidian-to-Anki solution or something (don't know if one even exists).

I used Anki for years, not for Geoguessr, but I've been a fan of spaced repetition for a long time.

It worked well and has a great community, but I found the process for creating cards was outside my main note taking flow, and when I became more and more integrated into Obsidian I eventually investigated how to switch. As soon as I did, I've never needed Anki, although there have been a few times I wished I could use their pre-made decks.

I know there are integrations that go both ways. I built a custom tool to take Anki decks and modify them to work with my Obsidian Spaced Repetition plugin. I don't have a need to go the other way at the moment but I've seen other tools that do that.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#399

Post by noname120 »

qarl wrote: post #104

> I’m confident it didn’t cheat and look at the EXIF data on the photograph, because if it had cheated it wouldn’t have guessed Cambria first. It also, at one point, said it couldn't see any image data at all. You absolutely cannot trust what it says. You need to re-run with the EXIF data removed.

Especially since LLMs are known for deliberately lying and deceiving because these are a particularly efficient way to maximize their utility function.

Re: Watching o3 guess a photo's location is surreal, dystopian and entertaining

#400

Post by SamPatt »

cyanbane wrote: post #351
SamPatt wrote: post #63

I play competitive Geoguessr at a fairly high level, and I wanted to test this out to see how it compares. It's astonishingly good. It will use information it knows about you to arrive at the answer - it gave me the exact trailhead of a photo I took locally, and when I asked it how, it mentioned that it knows I live nearby. However, I've given it vacation photos from ages ago, and not only in tourist destinations eit…

Have you gleaned anything watching o3 make decisions on a photo? ( i.e. have you noticed if it has thought of anything you.. and other higher level players similar to you... have not? )

This is an interesting question.

I watch the output with fascination, mostly because of the sheer breadth of knowledge. But thus far I can't think of anything that is categorically different from what humans do, it's just got an insane amount of knowledge available to it.

For example, I gave it an image from a town on a small Chilean island. I was shocked when it nailed it, and in the output it said, "I can see a green wooden street sign, common to Chilean coastal towns on [the specific island]."

I have an entire flashcard section for street signage, but just for practicality I'm limited to memorizing scores, possibly hundreds of signs if I'm insanely dedicated. I would still probably never have this one remote Chilean island.

It does that for everything in every category.

Post reply on HN