Wow yes, Gemini one-shot this in a fraction of the time, with 100% accuracy
I guess the Nano image-tech does pay off for Google sometimes
Posts by Gergő Bocsárdi
Super interesting to see how something that I think is pretty trivial (match grids on images) could be so tough
It had a hard time differentiating pale fish from silhouettes (makes sense), but then some places it just completely was off the mark
Wondering if Gemini would do better, with Nano
Picture of my incomplete fish collection in Stardew Valley on the collection page
reference picture of a full collection with fish names labeled
So I asked a Claude Opus 4.6 to take these two images, cross-check what's missing for me, and generate me a checklist, and it ABSOLUTELY LOST THE PLOT
It went through 60% of my 5-hour Pro plan window, kept second guessing itself, and didn't manage, in the end it created a JSX to get my input😃
I’m gonzo for AI and this is a good idea. Wikipedia belongs to a deeper pace layer. Critical infrastructure. Move slow, edit things.
I've said similar things before, but with respect to the question of whether GenAI is a "transformative" technology, I think the bar should be: the person who refuses to use it for the application(s) it transforms can be judged as irrational in ways that do not boil down to personal preference.
@hankgreen.bsky.social considering that I think of your "printing press as media revolution" video at least weekly, I'd love to hear your thoughts on the AI printing press parallel!
i think the main reason is that with the algo-rot in the past few years the effect of "long scrolling" feels indistinguishable from "long scrolling terrible news"
they both make people miserable, and with the amount of attention engineering implemented stopping is difficult
Hahaha funny you should say that, I switched to WezTerm from Ghostty because Ghostty's native tabs kept messing up Aerospace, and I'm more attached to my WM than my terminal😃
I embarked on the journey of reading through all of Kurt Vonnegut's novels, starting with Player Piano.
I'm 30% in and my God this book needs more hype in our AI-development era, all the themes around technology and it's relation to humans are painfully relevant today, 70 years later
After obtaining my math degree, my hot take became that math is part of the humanities, because it's much closer to a fully "made up" l'art pour l'art pursuit of beauty (such as poetry or lit) than the grounded, pragmatic problem solving of engineering
It is indeed "good old fashioned AI", nowadays it refers to the pre-LLM era AI systems mostly😃
And while I enjoy playing with LLMs, I certainly meant it as a compliment hahahaha
This is super cool! A bit of an antithesis to stable diffusion, the image version of GOFAI😃
Art galleries a bit weird eh. Each time your visit, a 100 paintings scattered in rooms and you walk through like uh-huh, uh-huh, ok, that’s nice, uh-huh, ok. Then at random one of them skewers you through your soul and you’re transfixed by the image for life
the year of linux desktop is upon us, just slapped a linux mint on my mother’s old laptop, instead of win11😃
This is unexpectedly delightful: a dying mall in Portland Oregon is filling up with a beautiful collection of weird and interesting businesses because the rent is now affordable for them www.tiktok.com/@hereisorego...
memes aside, with the lack of algorithm to me Bsky feels decidedly closer to my RSS feed than any sort of shortform brainrot
now it’s time for us to start betting on what you’ll get
@ssp.sh saw the convo on replacing raycast on arch, have you seen this one?😃
I forgot that I have a workshop proposal deadline tomorrow, so today I frantically wrote 2800 words😃
I guess that paper draft that I have been procrastinating on is now done💀 nothing gets me working like a deadline
old story in rob's head: ahhhhhhh i'm feeling super overwhelmed by my to do list, so i should prob run away and do a bunch of recreational numbing in the name of "self care"
new story: the more i do the better i feel
Any best practices for prompting the deep research?
I tried for the first time a few days ago, but it kept getting lost in “collecting additional data” endless web browse spirals, with 4-500 web pages opened, to complete the task of collecting submission guidlines of a list of academic journals😅
Today I tried to reconcile some rather ambivalent thoughts on LLMs, thinking, and work😃
Insanely cool setup!
But can it run Doom?😃
I realized I mostly just needed a formatter, so the injected language formatting feature of conform.nvim took care of this!
I just replicated a 40 minute processing pipeline from a spark cluster in 33 minutes on my macbook😃
I have to say I now get the hype
Or in the middle the @simonwillison.net -ism of “give me 10 ways to solve this problem” and then pick the one you like the most to code down!
I was looking for a dictation tool on my iphone that’s better than the built-in, but still not a cloud, and lo and behold, there is one!
I just tried superwhisper’s local model, and it provided me with flawless transcripts in both english and hungarian, all made locally.
yap walks here we come!!
Hahaha not exactly, though the source is all the same😃
I’m using Quarto’s website framework! This was basically anything I write (papers, blogposts, presentations) come from a single unified source of QMD files, just rendered differently
Found that it reduces a lot of friction around formats!
Just simple stuff I think, my site is a good example, it’s not even a VPS, just hosted storage and I push the generated files over via FTP😃
Quarto’s revealjs is my go-to!
Only caveat with revealjs is that you need a Chrome to export nice PDFs (Safari and Firefox usually mangle the aspect ratios for me)
I certainly agree that taking steps to reduce environmental impact is necessary, but I think the main point is more that ChatGPT usage isn’t a Big New High-Impact Thing, rather than a drop in an already pretty large bucket, which itself deserves more attention.