Hacker News: iamanllm

New comment by iamanllm in "RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8"

iamanllm — Sun, 14 Jun 2026 12:22:21 +0000

yeah, the "proactivity" of recent anthropic models and sophisticated bullshitting are bad, although my experience is that even on simple tasks i've never used a oss model that has consistently been better in terms of the quality of the result.

New comment by iamanllm in "RTX 5080 and RTX 3090 Setup: 80 Tok/s on Qwen 3.6 27B Q8"

iamanllm — Sun, 14 Jun 2026 08:57:16 +0000

Frontier models are still better (everyone would use them if it was cheap). Open source models are capable on even non "simple" problems but I trust them less, even though I usually write plans for all changes, and they are worse at debugging. I recently converted my homelab to nixos and let's just say Deepseek failed and Fable did great (the night before getting killed)

New comment by iamanllm in "For thirty years I programmed with Phish on, every day"

iamanllm — Mon, 04 May 2026 05:28:10 +0000

As a phish fan, this is an especially sad read. I wonder what new developers might feel, if they have the same sense of wonder and joy, listening to a brand new jam, working with an agent to create something, learning a thing or two about development, and being proud. I hope so.

New comment by iamanllm in "Show HN: I trained a 9M speech model to fix my Mandarin tones"

iamanllm — Sat, 31 Jan 2026 03:53:36 +0000

holy crap, I was literally imaging how I wanted something exactly like this yesterday! you are a hero!

New comment by iamanllm in "ASCII-Driven Development"

iamanllm — Sun, 11 Jan 2026 02:54:15 +0000

it's not formal writing it's a blog post.

New comment by iamanllm in "ASCII-Driven Development"

iamanllm — Sat, 10 Jan 2026 20:58:27 +0000

"Not as an aesthetic choice. Not as nostalgia. But as a thinking tool" is a perfectly normal sentence, and I think there is an equally bad trend of people assuming things are AI written and forget that AI was trained on human writing. But to your point, agreed there is a disconnect when things are in fact written by AI, but I skimmed the article anyway so to me it didn't matter lol.