Hacker News: johnnyyyy

New comment by johnnyyyy in "AI coding"

johnnyyyy — Sun, 14 Sep 2025 11:34:55 +0000

In your blog post: “Most people do not care to find the truth, they care about what pumps their bags”

in your HN comment: “I agree with this comment, but if I wrote more like this my blog post would get less traction.”

Seems like you also not care about the truth.

New comment by johnnyyyy in "The Zed Debugger Is Here"

johnnyyyy — Thu, 19 Jun 2025 18:00:20 +0000

The developer of Ghostty is using AI for development. Better quickly delete it!

New comment by johnnyyyy in "OpenAI dropped the price of o3 by 80%"

johnnyyyy — Wed, 11 Jun 2025 12:22:56 +0000

then you shouldn’t use OpenRouter. ToS: 4.2 Credit Expiration; Auto Recharge OpenRouter reserves the right to expire unused credits three hundred sixty-five (365) days after purchase

New comment by johnnyyyy in "Show HN: I built an AI that turns GitHub codebases into easy tutorials"

johnnyyyy — Sun, 20 Apr 2025 17:23:25 +0000

Are you implying that only the creator of the code can write documentation?

New comment by johnnyyyy in "CSS gets a new logo and it uses the color `rebeccapurple`"

johnnyyyy — Mon, 18 Nov 2024 11:39:03 +0000

But did you really forget it if you remember that you read this already?

Did you really forgot why its called rebeccapurple?

New comment by johnnyyyy in "New Mac Mini with M4"

johnnyyyy — Thu, 31 Oct 2024 00:36:44 +0000

Wait about what kind of people are you talking about and how niche is that target group?

You are saying Mac are expensive but at the same time the potential buyers cant afford even a cheap 4K monitor? They go by like 200$? now. and even is that group exists.. its not like 2560p is torture on a Mac especially with that BetterDisplay HiDPI, I would bet many would not even notice the difference.

New comment by johnnyyyy in "Study: ChatGPT outperforms physicians in quality, empathetic answers to patients"

johnnyyyy — Sat, 29 Apr 2023 17:48:05 +0000

I doubt you would be better than someone who would use Stable Diffusion for 7 years. and I don’t even include the technological advancements in the next 7 years.

ChatGPT API – How do I handle the 4000 token limit for keeping context?

johnnyyyy — Sun, 05 Mar 2023 13:56:27 +0000

I am coding a little Discord ChatGPT Bot that I just want to privately use. Right now I just feed the whole message history back to ChatGPT but of course you quite quickly reach the 4000 token limit.

The simplest solution of course would be to just delete the oldest messages but that of course could delete more important messages.

Another idea was that I could let ChatGPT summarise the conversation when I am close to the limit and then only save that message.

Maybe theres already some better implementation that I am not aware of?

Comments URL: https://news.ycombinator.com/item?id=35029610

Points: 3

# Comments: 1