dmd (u/dmd) - Readit News

dmd commented on A 'toaster with a lens': The story behind the first handheld digital camera bbc.com/future/article/20... · Posted by u/selvan

pavlov · 12 hours ago

Digital photography is one of those innovations that wonderfully ages pre-1990s science fiction where people of distant futures still fiddle with film chemicals.

The first book of David Brin’s Uplift series was written in 1980 and takes place on an antigravity spaceship carrying alien ambassadors that can penetrate deep into the Sun. Yet one of the major plot points is someone using the onboard darkroom to develop pictures that reveal something essential.

I’m hoping someone would make a new sci-fi movie with a vintage aesthetic that would intentionally emphasize and magnify this old-school analog awesomeness of galactic empires that seem to entirely lack integrated circuits. Apple TV’s “Silo” has a wonderful production design but it’s too claustrophobic to fulfill my wish.

“The Mote in God’s Eye” would be my pick if I could get any IP developed with this approach.

dmd · 9 hours ago

> old-school analog awesomeness of galactic empires that seem to entirely lack integrated circuits

Reminds me of Harry Turtledove's The Road Not Taken.

https://en.wikipedia.org/wiki/The_Road_Not_Taken_(short_stor...

dmd commented on Ask HN: How can I get better at using AI for programming? · Posted by u/lemonlime227

bcherny · 12 hours ago

Hey, Boris from the Claude Code team here. A few tips:

1. If there is anything Claude tends to repeatedly get wrong, not understand, or spend lots of tokens on, put it in your CLAUDE.md. Claude automatically reads this file and it’s a great way to avoid repeating yourself. I add to my team’s CLAUDE.md multiple times a week.

2. Use Plan mode (press shift-tab 2x). Go back and forth with Claude until you like the plan before you let Claude execute. This easily 2-3x’s results for harder tasks.

3. Give the model a way to check its work. For svelte, consider using the Puppeteer MCP server and tell Claude to check its work in the browser. This is another 2-3x.

4. Use Opus 4.5. It’s a step change from Sonnet 4.5 and earlier models.

Hope that helps!

dmd · 9 hours ago

I would LOVE to use Opus 4.5, but it means I (a merely Pro peon) can work for maybe 30 minutes a day, instead of 60-90.

dmd commented on What folk can do folk.computer/guides/what... · Posted by u/luu

dmd · 2 days ago

folk can return a 502 error, apparently.

dmd commented on GPT-5.2 openai.com/index/introduc... · Posted by u/atgctg

austhrow743 · 2 days ago

We've been having trouble telling if people are using the same product ever since Chat GPT first got popular. The had a free model and a paid model, that was it, no other competitors or naming schemes to worry about, and discussions were still full of people talking about current capabilities without saying what model they were using.

For me, "gemini" currently means using this model in the llm.datasette.io cli tool.

openrouter/google/gemini-3-pro-preview

For what anyone else means? If they're equivalent? If Google does something different when you use "Gemini 3" in their browser app vs their cli app vs plans vs api users vs third party api users? No idea to any of the above.

I hate naming in the llm space.

dmd · 2 days ago

FWIW i’m always using 5.1 Thinking.

dmd commented on GPT-5.2 openai.com/index/introduc... · Posted by u/atgctg

staticman2 · 2 days ago

Are you uploading PDFs that already have a text layer?

I don't currently subscribe to Gemini but on A.I. Studio's free offering when I upload a non OCR PDF of around 20 pages the software environment's OCR feeds it to the model with greater accuracy than I've seen from any other source.

dmd · 2 days ago

I’m not uploading PDFs at all. I’m talking about PDFs it finds while searching than it extracts data from for the conversation.

dmd commented on GPT-5.2 openai.com/index/introduc... · Posted by u/atgctg

nullbound · 2 days ago

I will say that it is wild, if not somewhat problematic that two users have such disparate views of seemingly the same product. I say that, but then I remember my own experience just from few days ago. I don't pay for gemini, but I have paid chatgpt sub. I tested both for the same product with seemingly same prompt and subbed chatgpt subjectively beat gemini in terms of scope, options and links with current decent deals.

It seems ( only seems, because I have not gotten around to test it in any systematic way ) that some variables like context and what the model knows about you may actually influence quality ( or lack thereof ) of the response.

dmd · 2 days ago

And I’d really like for Gemini to be as good or better, since I get it for free with my Workspace account, whereas I pay for chatgpt. But every time I try both on a query I’m just blown away by how vastly better chatgpt is, at least for the heavy-on-searching-for-stuff kinds of queries I typically do.

dmd commented on GPT-5.2 openai.com/index/introduc... · Posted by u/atgctg

tenpoundhammer · 2 days ago

I have been using chatGPT a ton over the last months and paying the subscription. Used it for coding, news, stock analysis, daily problems, and a whatever I could think of. I decided to give Gemini a go when version three came out to great reviews. Gemini handles every single one of my uses cases much better and consistently gives better answers. This is especially true for situations were searching the web for current information is important, makes sense that google would be better. Also OCR is phenomenal chatgpt can't read my bad hand writing but Gemini can easily. Only downsides are in the polish department, there are more app bugs and I usually have to leave the happen or the session terminates. There are bugs with uploading photos. The biggest complaint is that all links get inserted into google search and then I have to manipulate them when they should go directly to the chosen website, this has to be some kind of internal org KPI nonsense. Overall, my conclusion is that ChatGPT has lost and won't catch up because of the search integration strength.

dmd · 2 days ago

I consistently have exactly the opposite experience. ChatGPT seems extremely willing to do a huge number of searches, think about them, and then kick off more searches after that thinking, think about it, etc., etc. whereas it seems like Gemini is extremely reluctant to do more than a couple of searches. ChatGPT also is willing to open up PDFs, screenshot them, OCR them and use that as input, whereas Gemini just ignores them.

dmd commented on Italy's longest-serving barista reflects on six decades behind the counter reuters.com/lifestyle/cul... · Posted by u/NaOH

forinti · 4 days ago

I once decided to plot my salaries corrected for inflation and found out that they only really went up a couple of times in 30 years.

dmd · 4 days ago

I’ve done this as well. I’m only making twice what I was 30 years ago at 18. (Though to be fair, I was making a ridiculous amount of money for a 18 year old - my first job was in the Qwest network operations center.)

dmd commented on US could ask foreign tourists for five-year social media history before entry bbc.co.uk/news/articles/c... · Posted by u/neversaydie

OccamsMirror · 4 days ago

I wonder if they'll accept "all I have is a Hacker News account".

dmd · 4 days ago

Hacker? Straight to jail.