Hacker News: grahammccain

New comment by grahammccain in "Gloomberb"

grahammccain — Thu, 13 Aug 2026 16:13:21 +0000

I don't think the finance field needs a better bloomberg, I think the whole interface and everything needs to be rethought. Part of the moat is the data, and data access. But I think we need to completely reimagine the terminal interface and interactions with the introduction of AI. The finance industry probably will be slow to adapt, but I genuinely think someone could completely disrupt 99% of the wall street businesses with an original idea.

New comment by grahammccain in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

grahammccain — Sat, 13 Jun 2026 14:11:26 +0000

I think my issue here, is that there is some dislike from each other from the administration and anthropic and it’s hard to figure out what part that is playing in this vs really there are bio and cyber security problems. I think personally I would like the models so I can keep building and it’s super upsetting it got ripped away like this.

New comment by grahammccain in "Ask HN: What are you working on? (May 2026)"

grahammccain — Mon, 11 May 2026 14:49:56 +0000

Chartlibrary.io - an intelligence layer for AI agents rooted in chart pattern search. Return 500 similar stock charts to the one you a looking at. Give those distributions stats to an agent, disect into buckets by variables. I think it’s a new way to interact with stocks for the agentic world.

New comment by grahammccain in "Serving a website on a Raspberry Pi Zero running in RAM"

grahammccain — Fri, 08 May 2026 20:22:02 +0000

I’ve wanted to get into raspberry pi builds for a long time. Off to order one now and try this.

New comment by grahammccain in "Show HN: Filling PDF forms with AI using client-side tool calling"

grahammccain — Sat, 02 May 2026 10:17:03 +0000

Keep going though. I’m definitely looking for something like this once we can get something secure we can use with proprietary and pii data.

New comment by grahammccain in "Ask HN: Is GitHub's #1 repo fake? build-your-own-x 491K stars"

grahammccain — Tue, 21 Apr 2026 10:38:32 +0000

This is super interesting. Thanks for the read this morning.

New comment by grahammccain in "Ask HN: What would you do with an AI model capable of continuous learning?"

grahammccain — Fri, 10 Apr 2026 01:06:00 +0000

have it watch a bunch of stock charts at once, see if it could find edge.

New comment by grahammccain in "Ask HN: What's your favorite number, and why?"

grahammccain — Mon, 30 Mar 2026 20:48:53 +0000

3. It was my first soccer jersey number.

New comment by grahammccain in "Ask HN: How are you keeping AI coding agents from burning money?"

grahammccain — Sun, 29 Mar 2026 10:56:40 +0000

Kinda of an adjacent question but do you think the token/usage way of paying for things will stick? I still think people would rather pay a monthly subscription for a seat.

New comment by grahammccain in "The risk of AI isn't making us lazy, but making "lazy" look productive"

grahammccain — Sun, 29 Mar 2026 10:54:19 +0000

Productivity can’t be faked. Productivity also mostly aligns with incentives in my opinion. You want someone to be productive then give them a reason to be.

New comment by grahammccain in "We haven't seen the worst of what gambling and prediction markets will do"

grahammccain — Sat, 28 Mar 2026 17:58:30 +0000

They really need to regulate this things. Like people could spoof markets and stuff so easily. Do things that would be traditionally illegal in regular markets but not predication markets.

New comment by grahammccain in "Folk are getting dangerously attached to AI that always tells them they're right"

grahammccain — Sat, 28 Mar 2026 17:53:12 +0000

I feel like this is the same as social media problem. Some people will be able to understand that AI telling them they are right doesn’t make them right and some people won’t. But ultimately people like being told they are right and that sells, and brings back users.

New comment by grahammccain in "Ask HN: Is it just me?"

grahammccain — Sat, 28 Mar 2026 17:47:35 +0000

I definitely feel this exact sentiment. I’m wondering if it actually the model quality degrading or if it’s me lol.

New comment by grahammccain in "Show HN: For You – AI art floats down a river for strangers to find"

grahammccain — Fri, 27 Mar 2026 19:36:11 +0000

Super interesting will give it a try! Really interesting what the agents chose to do.

New comment by grahammccain in "Show HN: Veil – Dark mode PDFs without destroying images, runs in the browser"

grahammccain — Fri, 27 Mar 2026 14:06:41 +0000

Love this. Everything should be dark mode capable. Save the eyes!

New comment by grahammccain in "Show HN: Deep Hollow – A survival game where your AI runs your fortress 24/7"

grahammccain — Fri, 27 Mar 2026 14:02:53 +0000

This is a really cool idea. I’m curious if you get any wonky things happening with the AI while you are away from the world. Could be a good case study into the AI mind lol. Good job will have to check it out.

New comment by grahammccain in "GitHub now requiring 2FA for all contributors,what authenticator apps you using?"

grahammccain — Fri, 27 Mar 2026 14:01:28 +0000

I only use google and Microsoft, it might be a good idea for me to look into this deeper for the future.

New comment by grahammccain in "HyperAgents: Self-referential self-improving agents"

grahammccain — Fri, 27 Mar 2026 13:59:28 +0000

Being able to use new tools in ways we didn’t think of has been a great part of my experience with Claude.

New comment by grahammccain in "Hold on to Your Hardware"

grahammccain — Fri, 27 Mar 2026 12:57:55 +0000

I feel like we will get out of the hardware constraints eventually.

Ask HN: What are some ways you have limited AI slop

grahammccain — Wed, 25 Mar 2026 11:56:56 +0000

Coming from a non coding background, I’m curious if anyone has some tips to limit the AI slop while using Claude code. Also open to other use cases with AI coding tools.

Comments URL: https://news.ycombinator.com/item?id=47516155

Points: 1

# Comments: 1