Hacker News: seunosewa

New comment by seunosewa in "YouTube to automatically label AI-generated videos"

seunosewa — Thu, 28 May 2026 00:02:31 +0000

AI has completely ruined animal short videos on Youtube. Videos of pets behaving like humans are everywhere. At first they warm your heart, then you realize that you've been tricked.

New comment by seunosewa in "If AI writes your code, why use Python?"

seunosewa — Tue, 12 May 2026 14:37:23 +0000

What do you mean? Those are valid identifiers but programmers aren't required to use them.

New comment by seunosewa in "If AI writes your code, why use Python?"

seunosewa — Tue, 12 May 2026 14:22:20 +0000

Less verbose languages also use fewer tokens, saving precious context.

New comment by seunosewa in "Grok 4.3"

seunosewa — Fri, 01 May 2026 15:29:42 +0000

They dropped the output cost, butthe input cost is relatively high. This is a recent trend. Seen with DeepSeek 4 Pro as well.

New comment by seunosewa in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

seunosewa — Tue, 21 Apr 2026 04:30:13 +0000

API costs are really high compared to subs.

New comment by seunosewa in "Google releases Gemma 4 open models"

seunosewa — Sat, 04 Apr 2026 20:59:12 +0000

Now try to use it to develop a simple app.

New comment by seunosewa in "Axios compromised on NPM – Malicious versions drop remote access trojan"

seunosewa — Tue, 31 Mar 2026 15:35:39 +0000

We could have different Python package bundles: Python base. Python webdev. Python desktop.

New comment by seunosewa in "Axios compromised on NPM – Malicious versions drop remote access trojan"

seunosewa — Tue, 31 Mar 2026 15:33:01 +0000

requests should be in the Python standard library. Hard choices need to be made.

New comment by seunosewa in "$500 GPU outperforms Claude Sonnet on coding benchmarks"

seunosewa — Fri, 27 Mar 2026 17:53:36 +0000

Or just change the reasoning levels.

New comment by seunosewa in "$500 GPU outperforms Claude Sonnet on coding benchmarks"

seunosewa — Fri, 27 Mar 2026 13:07:17 +0000

Create it!

New comment by seunosewa in "OpenCode – Open source AI coding agent"

seunosewa — Sat, 21 Mar 2026 18:24:14 +0000

Successful vibe coders read code.

New comment by seunosewa in "OpenCode – Open source AI coding agent"

seunosewa — Sat, 21 Mar 2026 11:13:20 +0000

I'd suggest Go ahead of Rust. It's more accessible to contributors.

New comment by seunosewa in "Cursor Composer 2 is just Kimi K2.5 with RL"

seunosewa — Fri, 20 Mar 2026 11:56:27 +0000

Antigravity has an autocomplete model too. Based on Windsurf's, I guess.

New comment by seunosewa in "How I write software with LLMs"

seunosewa — Mon, 16 Mar 2026 15:57:58 +0000

After such hard-won wins, ask the AI to save what it learned during the session to a MD file.

New comment by seunosewa in "The MacBook Neo"

seunosewa — Wed, 11 Mar 2026 21:22:52 +0000

Large Java apps like Android Studio are not good at managing 8gb of RAM. Emulators are terrible as well. They don't play well with the swap feature.

New comment by seunosewa in "Agents that run while I sleep"

seunosewa — Wed, 11 Mar 2026 16:27:01 +0000

Unless what you want to do isn't well represented in the training set.

New comment by seunosewa in "Anthropic tries to hide Claude's AI actions. Devs hate it"

seunosewa — Mon, 16 Feb 2026 13:05:07 +0000

Perhaps they can just make it an option??

New comment by seunosewa in "GPT‑5.3‑Codex‑Spark"

seunosewa — Thu, 12 Feb 2026 20:16:54 +0000

How did you verify it?

New comment by seunosewa in "AI makes the easy part easier and the hard part harder"

seunosewa — Mon, 09 Feb 2026 17:33:53 +0000

Once you've gone through that, you might want to ask it to codify what it learned from you so you don't have to repeat it next time.

New comment by seunosewa in "Claude Opus 4.6"

seunosewa — Thu, 05 Feb 2026 22:38:25 +0000

They introduced the low limit warning for Opus on claude.ai