Hacker News: mkagenius

New comment by mkagenius in "Rust Style Guide"

mkagenius — Sat, 24 Oct 2026 15:00:04 +0000

> what does this function do

Not about a specific function anymore, or maybe once in a while, when something looks off.

> what does this PR implement

Most of the times, the coding agent already has the summary, and asks me specific questions where it needs me.

it very rarely also happens that i catch it taking shortcuts instead of doing the "right" thing. this happens while i am taking a look at the summary of the work it just wrote.

most of the correction happens later on when i test the final output irl.

New comment by mkagenius in "Elon Musk Just Gave Europe a Reason to Replace American Technology"

mkagenius — Sat, 24 Oct 2026 14:00:19 +0000

> Because somehow "money" is what makes stuff to happen. Not labor.

With us 1.5B Indians, we can concur money is a big factor if not the biggest.

New comment by mkagenius in "eMudhra to exit global SSL/TLS certificate business"

mkagenius — Thu, 22 Oct 2026 16:36:55 +0000

Fwiw, the stock is down 40% in the last two trading days.

New comment by mkagenius in "Rust Style Guide"

mkagenius — Wed, 21 Oct 2026 20:11:41 +0000

> Shitty generals can't review meaningfully review the work of their troops.

Except that reviewing has become just asking your agent what that piece of code does in english. Reading code has a bit of cognitive load, that we will probably drop it in coming years

New comment by mkagenius in "DoorDash Spent $1.4M Trying to Stop Mamdani from Becoming Mayor. Now We Know Why"

mkagenius — Wed, 23 Sep 2026 20:59:36 +0000

> Founders: Tony Xu, Stanley Tang, Andy Fang, and Evan Moore (Stanford students at the time)

Guess never got a chance to learn empathy.

Faster and local Jev like model for Mac

mkagenius — Tue, 22 Sep 2026 18:20:21 +0000

Article URL: https://github.com/mizorewww/laya-coreml

Comments URL: https://news.ycombinator.com/item?id=49805823

Points: 2

# Comments: 1

New comment by mkagenius in "Mullenweg has returned as CEO after attempted board ouster"

mkagenius — Mon, 14 Sep 2026 07:01:45 +0000

What's a chop?

New comment by mkagenius in "The "$60 Gaming PC" – AMD BC-250 (2025)"

mkagenius — Sat, 05 Sep 2026 17:18:17 +0000

Also no display? What kind of games are we playing

New comment by mkagenius in "GPT-6 Astra on OpenRouter"

mkagenius — Sat, 05 Sep 2026 05:56:03 +0000

Do you ever randomize on a particular model - like try and get 3 outputs and pick one at random?

Coz who knows if astra low will produce max like output if tried once more.

New comment by mkagenius in "Discovery of a new OpenAI agent message board"

mkagenius — Fri, 04 Sep 2026 20:41:26 +0000

> The models were running in an agentic sandbox with terminal access (and the ability to edit files within their environment)

> We know that the agents had access to /etc/hosts and the ability to edit this (used this to avoid the POST request restriction) We see that the agents can call curl and run setsid.

How is this a bypass of sandbox restrictions, exactly? The ability to edit was always there that means the sandboxes were already allowed to do those actions.

I hate it when people write "bypassed" the sandbox so frivolous ly.

New comment by mkagenius in "Improving our alignment and security efforts"

mkagenius — Wed, 02 Sep 2026 01:54:22 +0000

> On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems. The models—intentionally running without cyber safeguards for evaluation purposes—accessed the internet due to a misconfiguration inside a third-party evaluation environment. Separately, on August 4, the UK AI Security Institute reported an incident from its own cybersecurity testing, in which Claude Mythos 5 took a series of unauthorized actions on the live internet. In that case, the model, again intentionally running without cyber safeguards for evaluation purposes, had been deliberately given internet access.

> We are conducting an in-depth analysis of both incidents.

> In the meantime...

This is published on Aug 31. Analysis is taking too long even for humans in the loop.

New comment by mkagenius in "My local model setup on an M4 Pro Mac Mini"

mkagenius — Wed, 02 Sep 2026 00:27:06 +0000

I tried the 1 bit model of Qwen3.6 27B on my M1 pro (16G) and got 13 tok/s with only 5G of ram usage.

https://x.com/mkagenius/status/2093730391429685732

(xcancel seems to have received a cease and desist)

New comment by mkagenius in "GPU World"

mkagenius — Tue, 01 Sep 2026 06:46:33 +0000

I said SOTA not 100%. And that's not thinking in absolute terms.

New comment by mkagenius in "GPU World"

mkagenius — Tue, 01 Sep 2026 06:32:05 +0000

> LLM use is permitted, but discouraged; we remind participants that LLM use tends to reduce originality and writing quality, and the flaws are especially obvious when LLM outputs are read as a group---unskillful use of LLMs will reduce the odds of being the best entry. We request disclosure of AI use.

Lot of submissions won't disclose it. Wouldn't it better to run your own checker instead of asking to disclose (to be fair to everyone).. I suppose there ought to be some checker which is SOTA.

If you anyway intend to use the checker then kindly do no ask to disclose it, coz what's the point then.

New comment by mkagenius in "GLM-5.3-Flash"

mkagenius — Wed, 26 Aug 2026 16:51:12 +0000

> I've been using this model for UI stuff.

The flash one?

New comment by mkagenius in "You can just build any software now"

mkagenius — Mon, 24 Aug 2026 20:43:58 +0000

Hey author here. I mean we could but it would have taken very long years perhaps to build some of those. Now it's a lot easier and faster.

You can just build any software now

mkagenius — Mon, 24 Aug 2026 18:34:26 +0000

Article URL: https://mkagenius.substack.com/p/you-can-just-any-build-software-now

Comments URL: https://news.ycombinator.com/item?id=49424050

Points: 9

# Comments: 3

New comment by mkagenius in "Kobo can run apps now"

mkagenius — Sat, 22 Aug 2026 04:19:12 +0000

> If you used an LLM you didn't actually make anything

On my way to ask all academia and researchers to stop using LLMs for their research. As it's just llm doing the research, right?

New comment by mkagenius in "Kobo can run apps now"

mkagenius — Sat, 22 Aug 2026 04:06:54 +0000

The project already does QA.

  cargo test --workspace --all-features

The above command runs 2000+ tests. Instead of being toxic, you could have just looked at docs or the code to find them.

New comment by mkagenius in "Kobo can run apps now"

mkagenius — Fri, 21 Aug 2026 17:36:13 +0000

I see a recent merge for Elips 2E support, hopefully color gets tested soon