Hacker News: flux3125

New comment by flux3125 in "Show HN: Continue? Y/N: A 60-second game about AI agent permission fatigue"

flux3125 — Thu, 28 May 2026 16:46:46 +0000

> It's also never deleted anything it shouldn't or done anything crazy or unrelated to what I asked

Until it does. A simple curl request to a compromised website could inject a malicious prompt into it.

New comment by flux3125 in "I let AI build a tool to help me figure out what was waking me up at night"

flux3125 — Tue, 12 May 2026 11:22:23 +0000

> Don't listen to him

That's the idea

New comment by flux3125 in "LLMorphism: When humans come to see themselves as language models"

flux3125 — Sun, 10 May 2026 14:00:07 +0000

You're absolutely right!

New comment by flux3125 in "A web page that shows you everything the browser told it without asking"

flux3125 — Fri, 08 May 2026 16:50:45 +0000

At least it doesn't know my age

Oh wait

New comment by flux3125 in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

flux3125 — Mon, 20 Apr 2026 18:06:35 +0000

Point 2 is so true, I definitely find myself spending more time reading code vs writing it. LLMs can teach you a lot, but it's never the same as actually sitting down and doing it yourself.

New comment by flux3125 in "Building a Web Page That Edits Itself"

flux3125 — Fri, 17 Apr 2026 11:23:43 +0000

I was (positively) surprised that this didn't involve any AI.

New comment by flux3125 in "Codex for almost everything"

flux3125 — Thu, 16 Apr 2026 20:09:07 +0000

Code quality and IDEs aren't going anywhere, especially in complex enterprise systems. AI has improved a lot, but we're still far from a "forget about code" world.

New comment by flux3125 in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

flux3125 — Thu, 16 Apr 2026 14:59:56 +0000

They are okay for vibe coding throw-away projects without spending your Anthrophic/OAI tokens

New comment by flux3125 in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

flux3125 — Thu, 16 Apr 2026 14:32:52 +0000

You ARE the training data

New comment by flux3125 in "The local LLM ecosystem doesn’t need Ollama"

flux3125 — Thu, 16 Apr 2026 08:56:51 +0000

I stopped using Ollama a couple of months ago. Not out of frustration, but because llama.cpp has improved a lot recently with router mode, hot-swapping, a modern and simple web UI, MCP support and lots of other improvements.

New comment by flux3125 in "The local LLM ecosystem doesn’t need Ollama"

flux3125 — Thu, 16 Apr 2026 08:05:39 +0000

> so llama-swap can load

Just in case you haven't seen it yet, llama.cpp now has a router mode that lets you hot-swap models. I've switched over from llama-swap and have been happy with it.

New comment by flux3125 in "I ran Gemma 4 as a local model in Codex CLI"

flux3125 — Mon, 13 Apr 2026 20:12:58 +0000

In my experience if you're coding or doing something that requires precision, quantizing the kv cache is definitely not worth it.

If you're just chatting or doing less precise things it's 1000% worth it going down to Q8 or sometimes even Q4

New comment by flux3125 in "We've raised $17M to build what comes after Git"

flux3125 — Fri, 10 Apr 2026 15:21:11 +0000

> but with people throwing money behind it, there’s a plan to extract value from the user base from day one.

They'll start injecting ads in your commit messages, forcing you to subscribe to a premium plan.

New comment by flux3125 in "Show HN: TUI-use: Let AI agents control interactive terminal programs"

flux3125 — Wed, 08 Apr 2026 19:18:17 +0000

Finally Claude Code can now control Claude Code

New comment by flux3125 in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"

flux3125 — Wed, 08 Apr 2026 09:05:59 +0000

> dunno why you'd need such a silly thing though

I'm not sure I follow, what alternative to CUDA on Linux offers similar performance?

New comment by flux3125 in "Slightly safer vibecoding by adopting old hacker habits"

flux3125 — Wed, 08 Apr 2026 07:53:48 +0000

I remember someone on HN once saying they treat LLM agents like human coworkers, security-wise, and that stuck with me.

You don't give your GH keys, email credentials and ssh keys to a coworker. They have their own accounts with scoped permissions. Need them to read an email? Forward it. Need them to work on a repo? Add them as a contributor and enforce the same branch policies you would for any human.

There are still risks, but they're similar to delegating work to humans, so it's up to you how much access and trust to give.

New comment by flux3125 in "Sam Altman may control our future – can he be trusted?"

flux3125 — Tue, 07 Apr 2026 09:27:23 +0000

Interesting. If you look at the sources it cited, there are a few links about "Sacred Songs and Solos" (likely from related/side content on the page), my guess is it didn't read the main article and instead anchored on those and hallucinated

New comment by flux3125 in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"

flux3125 — Fri, 03 Apr 2026 14:36:04 +0000

to be fair, llama.cpp has gotten much easier to use lately with llama-server -hf . That said, the need to compile it yourself is still a pretty big barrier for most people.

New comment by flux3125 in "Google releases Gemma 4 open models"

flux3125 — Thu, 02 Apr 2026 18:39:04 +0000

That’s not what it means. "-it" just indicates the model is instruction-tuned, i.e. trained to follow prompts and behave like an assistant. It doesn’t imply anything about whether thinking tokens like .... were included or excluded during training. Thats a separate design choice and varies by model.

New comment by flux3125 in "Google releases Gemma 4 open models"

flux3125 — Thu, 02 Apr 2026 18:32:46 +0000

You're not doing anything wrong, that's expected