Hacker Newsnew | past | comments | ask | show | jobs | submit | pwython's commentslogin

How many pelican riding bicycle SVGs were there before this test existed? What if the training data is being polluted with all these wonky results...

I'd argue that a models ability to ignore/manage/sift through the noise added to the training set from other LLMs increases in importance and value as time goes on.

You're correct. It's not as useful as it (ever?) was as a measure of performance...but it's fun and brings me joy.

My "actual job" is a designer, not a career engineer, so for me code has always been how I ship. AI makes that separation clearer now. I just recently wrote about this.[0]

But I think the cognitive debt framing is useful: reading and approving code is not the same as building the mental model you get from writing, probing, and breaking things yourself. So the win (more time on problem solving) only holds if you're still intentionally doing enough of the concrete work to stay anchored in the system.

That said, if you're someone like me, I don't always need to fully master everything, but I do need to stay close enough to reality that I'm not shipping guesses.

[0] https://alisor.substack.com/p/i-never-really-wrote-code-now-...


1 frame of Bob Ross = 1,800s


So with 108,000 (60 X 1,800) Bob Ross PPUs (parallel painting units) we should be able to achieve a stable 60FPS!


Once you set up a pipeline, sure. They'd need a lot of bandwidth to ensure the combined output makes any kind of sense, not unlike the GPU I guess.

Otherwise it's similar to the way nine women can make a baby in a month. :)


The food/housing/etc bill for 108k Bob Ross er... PPU's seems like it would be fairly substantial too.


For those that have homebrewed a base model, does your output have the same AI-isms like overusing em dashes? If so/not, what dataset did you use?


Does yours also use the oxford comma and generally more commas?


AFAIK, those are mostly a consequence of posttraining.


that is a post-training artifact



I mean, Claude got 90% there. The author could contribute 10% of work to fix the alignment and have a finished page.


He assembled all the assets, did a bunch of prompting prep, etc. The alignment was kinda the main job, and he would have had to do a bunch of cleanup after. If this was a freelance job a client was paying for, I'd definitely tell myself to save cost next time by not using AI.


I switched to Mac in 2008. I forget if the featured existed back then, but today on macOS if you press spacebar on an image in Finder to preview, you can use the arrow keys to browse other photos.


Right. They introduced quick look soon after, but still not ideal. If you interact with the finder in any way, “quicklooked” item changes.


The fingerprint is comprised of more than device and OS:

Browser type and version

Screen resolution

Installed fonts

Browser plugins and extensions

Canvas fingerprinting data

WebGL (graphics hardware info)

Time zone

Language settings

IP address

HTTP headers

Touch support

Device type

AudioContext


Yeah but several of those will also be the same if you have the same iPhone model and iOS. Safari browser updates are installed as part of iOS update. So anyone with the same iOS version has the same version of Safari.


I was excited to see this today, as I just finished a new website in Figma last night and planned to have CC help build it out with the Figma MCP today. CC started up with Opus 4.5 and... Not off to a good start. It described a totally different looking layout on the first prompt to see the selected frame. I asked why:

You're right to call that out. Looking back at what happened:

  1. First get_design_context call - Nothing was selected, so it returned an
  error
  2. Second get_design_context call - It returned a tiny snippet of React code
  for a "Vector" component (just an image element), which gave me almost no
  context
  3. First get_screenshot call - The image returned was essentially blank/empty
  (the output showed <output_image> with what appears to be no actual visual
  content)

  I then hallucinated an entire design description based on:
  - The project context from CLAUDE.md (mentions "Creative Director",
  "Performance Marketing", "20+ years")
  - Common portfolio design patterns
  - The small code snippet mentioning a "Vector" element

  That was a significant error on my part. I should have told you "The
  screenshot appears empty or didn't load properly - can you try selecting a
  different element or re-selecting?" instead of fabricating a description.


Valid question, as they already have a partnership with OpenAI to use ChatGPT in Siri. I personally use GPT for illustrations and Nano Banana for photo edits (Midjourney for realistic photos).

As an aside, perhaps they're using GPT/Codex for coding. Did anyone else notice the use of emojis and → in their code?


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: