Hacker News: sneilan1

New comment by sneilan1 in "Ask HN: What Are You Working On? (March 2026)"

sneilan1 — Mon, 09 Mar 2026 02:04:11 +0000

I'm learning how to train transformer models locally to do useful work instead of having to pay for claude. I regularly update my blog here https://seanneilan.com/posts

New comment by sneilan1 in "New iPad Air, powered by M4"

sneilan1 — Mon, 02 Mar 2026 16:42:25 +0000

If it can be used for inference, who cares right? Just have claude vibe code some objective-C or run the Enclave app.

New comment by sneilan1 in "New iPad Air, powered by M4"

sneilan1 — Mon, 02 Mar 2026 16:41:34 +0000

That's very funny. Bravo.

New comment by sneilan1 in "Right-sizes LLM models to your system's RAM, CPU, and GPU"

sneilan1 — Mon, 02 Mar 2026 05:08:26 +0000

This is exactly what I needed. I've been thinking about making this tool. For running and experimenting with local models this is invaluable.

New comment by sneilan1 in "Latency numbers every programmer should know"

sneilan1 — Sat, 28 Feb 2026 14:20:25 +0000

Does anyone have Jeff Dean's sources for how he computed these numbers? What's the margin of error? How accurate are they now? Is there a set of numbers that also talks about memory bandwidth in GPUs? Are these numbers intel/amd only? How do they differ between an m1 architecture?

New comment by sneilan1 in "Statement on the comments from Secretary of War Pete Hegseth"

sneilan1 — Sat, 28 Feb 2026 04:10:03 +0000

I'm a lot happier now being an anthropic customer.

New comment by sneilan1 in "Anthropic drops flagship safety pledge"

sneilan1 — Thu, 26 Feb 2026 18:19:22 +0000

Yes, this is probably the piece I am not realizing. However, there is no better approach to getting more capital than by scaring people?

New comment by sneilan1 in "Anthropic drops flagship safety pledge"

sneilan1 — Thu, 26 Feb 2026 17:22:01 +0000

Yes, the CEO's of these AI companies are clearly not the people who should be selling AI products. They need to be hidden away and kept behind closed doors where they can do their best work. And they need advertising companies, PR firms and better marketing tactics to try and soothe the customers.

New comment by sneilan1 in "Anthropic drops flagship safety pledge"

sneilan1 — Thu, 26 Feb 2026 17:12:05 +0000

I don't understand why some of these AI companies check their egos at the door and hire public relations companies. Yes, I understand they are changing the world but customers do not open their wallets when they are scared. Very few people I know are as avant-guarde as I am with AI, but, most people look at these new technologies and simply feel fear. Why pay for something that will replace you?

New comment by sneilan1 in "What I Learned Using Local Vision Models for Scraping"

sneilan1 — Sun, 22 Feb 2026 00:18:07 +0000

Learned a lot about local models using them to scrape target.com.

What I Learned Using Local Vision Models for Scraping

sneilan1 — Sun, 22 Feb 2026 00:18:07 +0000

Article URL: https://seanneilan.com/posts/scraping-target-with-qwen/

Comments URL: https://news.ycombinator.com/item?id=47106601

Points: 2

# Comments: 1

New comment by sneilan1 in "Gas Town's agent patterns, design bottlenecks, and vibecoding at scale"

sneilan1 — Fri, 23 Jan 2026 16:51:08 +0000

I love it! I'm at level 6 and brave enough to try. I'm in. Giving this a shot!

New comment by sneilan1 in "Show HN: I built a text-based business simulator to replace video courses"

sneilan1 — Fri, 16 Jan 2026 14:25:09 +0000

This wins the internet today. Amazing work!!!

Show HN: Using Qwen3:1.7B to call itself recursively

sneilan1 — Fri, 16 Jan 2026 01:22:27 +0000

Hi, I got Qwen3:1.7b to execute it's own generated python code & then generate prompts to generate more python code recursively! In this case, it scrapes my website & then does it's own prompt engineering to make code to parse what it downloaded. Pretty basic but has some neat stuff in there. And all with Transformers.

Comments URL: https://news.ycombinator.com/item?id=46641868

Points: 1

# Comments: 0

New comment by sneilan1 in "Ask HN: What did you find out or explore today?"

sneilan1 — Thu, 15 Jan 2026 04:49:01 +0000

Published an edit today (post dated in Nov. but I've rewritten it 5x now) on my tutorial to use llama3.2:3b to generate fine tuning data to train tinyllama1.1b https://seanneilan.com/posts/fine-tuning-local-llm/ It took a while to figure out that when I made llama3.2 generate json, it didn't have enough horsepower to generate training data that was varied enough to successfully fine tune llama1.1b! Figured that out :) Something you never learn with the bigger models. Every token costs something even if it's a little bit.

New comment by sneilan1 in "Ask HN: Share your personal website"

sneilan1 — Wed, 14 Jan 2026 19:20:42 +0000

https://seanneilan.com

New comment by sneilan1 in "Eat Real Food"

sneilan1 — Wed, 07 Jan 2026 21:30:01 +0000

I'm so confused. Why would the United States care about people's health? It feels out of character for this administration given the times.

Claude Code CLI was broken

sneilan1 — Wed, 07 Jan 2026 20:25:51 +0000

Article URL: https://github.com/anthropics/claude-code/issues/16673

Comments URL: https://news.ycombinator.com/item?id=46532075

Points: 181

# Comments: 171

New comment by sneilan1 in "Meta Segment Anything Model 3"

sneilan1 — Thu, 20 Nov 2025 04:51:39 +0000

Have you found any models that work better for your use case?

New comment by sneilan1 in "Asus Ascent GX10"

sneilan1 — Mon, 10 Nov 2025 17:00:33 +0000

Does anyone have any information on how much this will cost? Or is it one of those products where if you have to ask you can't afford it.