Article URL: https://diffx.org/
Comments URL: https://news.ycombinator.com/item?id=44176737
Points: 35
# Comments: 3

Article URL: https://spectrum.ieee.org/biological-computer-for-sale
Comments URL: https://news.ycombinator.com/item?id=44175048
Points: 32
# Comments: 15

Article URL: https://jacobian.org/2025/jun/3/changing-directions/
Comments URL: https://news.ycombinator.com/item?id=44172659
Points: 32
# Comments: 7
Article URL: https://austinhenley.com/blog/coord2state.html
Comments URL: https://news.ycombinator.com/item?id=44175356
Points: 19
# Comments: 9

Article URL: https://www.preciousplastic.com//news/problems-in-precious-plastic
Comments URL: https://news.ycombinator.com/item?id=44175773
Points: 35
# Comments: 18
https://www.preciousplastic.com//news/problems-in-precious-plastic
Article URL: https://www.pnas.org/doi/10.1073/pnas.2416433122
Comments URL: https://news.ycombinator.com/item?id=44175905
Points: 50
# Comments: 7

Article URL: https://www.theregister.com/2025/06/03/meta_pauses_android_tracking_tech/
Comments URL: https://news.ycombinator.com/item?id=44175940
Points: 13
# Comments: 2
https://www.theregister.com/2025/06/03/meta_pauses_android_tracking_tech/
Was starting to mess around with the latest LLM models and found that they're not great at counting lines in files.
I gave Gemini 2.5 flash a python script and asked it to tell me what was at line 27 and it consistently got it wrong. I tried repeatedly to prompt it the right way, but had no luck.
https://g.co/gemini/share/0276a6c7ef20
Is this something that LLM bots are still not good at? I thought they had gotten past the "strawberry" counting problems.
Here's the raw file: https:/