Hacker Newsnew | past | comments | ask | show | jobs | submit | Fe2O3's commentslogin

"It's one of the resources I used recently. -shadcn" being the top testimony is so funny.

I do love some of these examples, but, and as others noticed, they do lack polish.


Haha, yea. I was so happy when he mentioned TypeUI in a tweeet. Agreed, will work on polishing.


Why are lists of three considered slop? I genuinely use it quite a bit because groups of three feel more memorable, satisfying, and persuasive. (<- list of three right there)


This seems really cool, and it actually increases intelligence than just speeding up inference. How does it convert latent reasoning into human readable text?


Same way current LLMs do it, it's just another decoder.


The GitHub issue is now a 404.

Archived at: https://web.archive.org/web/20261006025310/https://github.co...


Issues removed, and a notice: Currently running an internal code audit.


"Gosh, did my LLM just copy Photopea? Lemme see"


„Let me ask my LLM“


Copyright theft machine does copyright theft. Imagine that.


What do you think?


Hmmmm, I'm relatively new to FTC and robotics in general, but I'm kind of excited to see what happens. My team has heard rumors regarding that it will likely be a shooter game this year, which could make it relatively easier for the whole participation body.



I've been using Readest (https://web.readest.com/) but I'll definitely be checking this out.


There's no way GPT 5.5 is better than GPT 5.6 Sol, and gemini-3.6-flash is better than both of those. I wouldn't trust this benchmark at all.


benchmark is saturated but your claim that gemini-3.6-flash is better than 5.6-sol is also not trustworthy or accurate.

maybe if you mentioned 3.7-flash it might have been slightly more believable (but still false).


He was remarking on how unbelievable it was. He sentence is a little bit hard to parse but he's saying that both 5.5 being better than 5.6 AND Gemini 3.6 scoring better than both are signs that this benchmark is not very useful.

The reason for both of those things is, as you point out, the benchmark is very obviously saturated


ah fair enough , 5.5 being better than 5.6 is just plain wrong and yeah makes everyone skeptical


Code.storage is able to handle large scales too: https://code.storage/

+-------------------------+-------------------------------+

| Total storage limit | Unlimited |

| Git request rate limits | Unlimited (Seen: 500+/s/repo) |

| API rate limits | Unlimited (Seen: 15k+/s) |

| Max repos | Unlimited |

| Concurrent writes | 30+ |

| Repository size limit | 32TB |

| Git LFS | Supported |

| GitHub/3rd party sync | Supported |

+-------------------------+-------------------------------+


WAT is the landing page all about, my brain can't process it. I had to close the tab after 10 seconds as I got immediate anxiety.


You made me look, are they on drugs?


So you work for them?


No, I just think it's a great concept and pricing seems good too.


Yeah GitHub could just migrate to your company tonight and everything would be fine by morning


Check out https://code.storage/

+-------------------------+-------------------------------+

| Total storage limit | Unlimited |

| Git request rate limits | Unlimited (Seen: 500+/s/repo) |

| API rate limits | Unlimited (Seen: 15k+/s) |

| Max repos | Unlimited |

| Concurrent writes | 30+ |

| Repository size limit | 32TB |

| Git LFS | Supported |

| GitHub/3rd party sync | Supported |

+-------------------------+-------------------------------+


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

Search: