Hacker News: kbrannigan

New comment by kbrannigan in "OpenCode 2.0"

kbrannigan — Wed, 14 Oct 2026 21:48:43 +0000

With websites i went back to 90s styles. Hyper dense in information. Anything clickable is a link. A button is for Write actions.

Interactive element are distinct from text.

If webpage page is an interactive canvas , make the canvas the main thing ad text as support.

If you start mixing the two idk..

New comment by kbrannigan in "A Modern Web App in C"

kbrannigan — Tue, 13 Oct 2026 05:45:59 +0000

Model are trained on them in 2026 .

Me Raw php .

Many people here have machines that can handle all of AOL , yahoo, msn of 2001 combined in their closet .

I have been going backwards in time as an experiment . I use mature extremely documented tools . Has to be at least 20 years old

New comment by kbrannigan in "Is mathematics over, or just graduating?"

kbrannigan — Tue, 06 Oct 2026 01:10:25 +0000

That is a very interesting perspective. What is the purpose of that corpus. Are all theorems or axioms useful?

New comment by kbrannigan in "Is mathematics over, or just graduating?"

kbrannigan — Tue, 06 Oct 2026 00:12:45 +0000

How big are mathematics? Is it as big as the universe?

New comment by kbrannigan in "Who is cleaning up all the garbage LLMs generate?"

kbrannigan — Mon, 05 Oct 2026 02:15:38 +0000

Hmm, hence the issue. It’s like chopping down a tree to make a box of matches. I wish the next generations of models don’t rely too much on markdown documentations which seems to be a human way of not writing code. Sometimes the code is just a little bit more structured to be honest , often times I feel like I might as well just write the code.

New comment by kbrannigan in "Who is cleaning up all the garbage LLMs generate?"

kbrannigan — Mon, 05 Oct 2026 02:12:23 +0000

What does that mean. Taking them down because the project failed or just replacing it?

Who is cleaning up all the garbage LLMs generate?

kbrannigan — Mon, 05 Oct 2026 01:22:29 +0000

So my one terabyte drive got full and I realized after months of CLI sessions I generated a lot of markdown files in a lot of images, all sort of other documents they all seem sorta kinda useful, and I too afraid to delete them because they might break something

How do you deal with that?

Comments URL: https://news.ycombinator.com/item?id=49959703

Points: 6

# Comments: 7

New comment by kbrannigan in "Ask HN: What Makes Tokens Expensive?"

kbrannigan — Thu, 17 Sep 2026 18:20:43 +0000

It's not always larger models. Often time it's a smaller model fit for a specific use case. In the future we will see 16B models that are for : Legal, Healthcare, Science, Software Engineering, Education, Forestry, Music production

New comment by kbrannigan in "Astra and Fable still hack on simple variants of alignment evals from 2025"

kbrannigan — Sun, 13 Sep 2026 16:14:35 +0000

Such a massive leap at averaging possible use cases from previous data collected.

My guess is : collect all the prompt and their satisfaction score. group them by similarity . For each group pretrain the next model on that . Get these results ready.

Next model generation feed them back those answers.

New comment by kbrannigan in "Ask HN: Would you hire a new engineer, or get 300k worth of tokens for the team?"

kbrannigan — Wed, 09 Sep 2026 03:54:46 +0000

I really would like to be a fly on wall during these executive meetings? Here is what i realized.

Spaghetti code written by 5 developers will need 5 + 1 developers to manage.

Same in the AI age spaghetti systems built by agents, will need a greater agent to untangle the mess that itself has created

New comment by kbrannigan in "Ask HN: Initial Thoughts on GPT-6 Astra?"

kbrannigan — Sat, 05 Sep 2026 03:19:18 +0000

First impression. It seems smarter at synthesing information faster. Something Gemini was really good at but it does it better.

It speaks more naturally, unlike claude which litteraly just vomit jargon and random analogies.

It's very expensive. After 15 message I burned through my 5 hour limits.

Demos online are very biased toward fancy user interfaces and animations and video games

New comment by kbrannigan in "Check if a file was made with Claude"

kbrannigan — Wed, 02 Sep 2026 14:13:42 +0000

How long before they change the terms and conditions to subtly claim ownership of your files? When you write code they already insert Co author attribution/

Say I write a text by hand And then I tell it to clean up the grammar and fix some sentences Did it make it?

This is also interesting for those companies that siphoned the entire open web

New comment by kbrannigan in "Claude Fable 5.1 and Claude Mythos 5.1"

kbrannigan — Tue, 01 Sep 2026 20:00:22 +0000

The human brain is fascinating Three years ago The idea of having A robot writing production level code in 10 minutes that would have needed a team of 5 people and 2 months. Was pure Scifi

Now it's boring , not good enough

Wow there should be a term of that .

New comment by kbrannigan in "Is it just me, or has Claude Opus gotten worse recently?"

kbrannigan — Tue, 01 Sep 2026 12:28:39 +0000

When it's overly verbose like that. Does that count against your usage as well? Also during its thinking does it output hidden thinking tokens?

I am now wondering

New comment by kbrannigan in "The brain may be about to have its Ozempic moment"

kbrannigan — Wed, 26 Aug 2026 02:18:22 +0000

To get a job at our company take three pills of brainOzempic every day to maximize productivity.

We have our NeuroLinkBrain Implant plugin to AI agent , so that you can vibe code 24/7 . To maximize shareholder value.

Ask HN: What AI companies provide human support?

kbrannigan — Mon, 24 Aug 2026 17:45:16 +0000

How can i run a small business that relies of many AI subscriptions, yet I am unable to get a human on the phone line to address an urgent concern.

or do they genuinely believe that AI is the support layer?

Comments URL: https://news.ycombinator.com/item?id=49423377

Points: 3

# Comments: 2

New comment by kbrannigan in "Anthropic's best AI model struggles to attract users as cheaper tools thrive"

kbrannigan — Mon, 24 Aug 2026 17:33:46 +0000

I'm not trust I was meant to be sarcastic or if you're serious I cant tell Is it true?

New comment by kbrannigan in "Anthropic's best AI model struggles to attract users as cheaper tools thrive"

kbrannigan — Mon, 24 Aug 2026 13:58:42 +0000

We used to get paid to code now we think we need to pay a subscription fee just to write software. They push marketing campaigns saying Manual coding no more, just vibe code, gain 10x speed for $100.

Then they hit you with hourly and weekly limits, you are wondering when you are going to get cut off. Since LLM at probabilistic it often feels like pulling the lever of a slot machine, hoping our prompt is the jackpot. To make sure we win, we come up with systems, convoluted agents, context pipelines, rags to load . It feels like it's working, then bam you reach weekly limits.

(Just pay more if you want to keep winning).

I think developers need to wake up.

I myself started to use AI like a fancy debugger ,explainer. I make it walk me though every single line of code it writes.

I notice that i run into limits less, if i get cutoff, i can still make changes

New comment by kbrannigan in "Anthropic's best AI model struggles to attract users as cheaper tools thrive"

kbrannigan — Mon, 24 Aug 2026 12:52:06 +0000

But it worked and it was so useful that LLM companies siphoned their data. It was how i learned programming

New comment by kbrannigan in "Anthropic's best AI model struggles to attract users as cheaper tools thrive"

kbrannigan — Mon, 24 Aug 2026 03:33:01 +0000

remember 4 year ago we use to : have stack overflow open, documentation, obscure forums plus other tabs.

An ide open with 20 tabs open each file a component, a class or an interface We also use to hold entire codebases in our brain.