Hacker News: 233mhz

New comment by 233mhz in "One month coding with GLM 5.3 Flash"

233mhz — Sat, 03 Oct 2026 20:58:33 +0000

And usage will grow accordingly, as usual.

My car engine is a miracle of efficiency compared to the stuff we had a hundred years ago, but overall cars pollute more than back then

New comment by 233mhz in "One month coding with GLM 5.3 Flash"

233mhz — Sat, 03 Oct 2026 20:56:50 +0000

> my house uses an average of 1300kWh per month.

And the average European house uses like 3000kwh.... per year. We're already wasting insane amount of energy, adding 2-10% more is definitely huge

New comment by 233mhz in "One month coding with GLM 5.3 Flash"

233mhz — Sat, 03 Oct 2026 20:52:13 +0000

This is a techie shit posting forum not a court of law, calm your tits down

New comment by 233mhz in "Getting the most out of Opus 5.5 in Claude and Claude Code"

233mhz — Sat, 03 Oct 2026 20:45:21 +0000

If enough people keep saying it I'm sure they will nerf it

New comment by 233mhz in "Gemini ending free use of Flash and Pro models"

233mhz — Sat, 03 Oct 2026 14:21:26 +0000

A lot of people don't see tech as a way to improve their life but some kind of fashion trend they have to keep up with. There also is the problem of people who were either bad devs or non dev at all who now get this omnipotent machine they can talk to in natural languages and it just does things for them, no matter how retarded the things are.

New comment by 233mhz in "DeepSeek Harness Desktop for macOS and Windows"

233mhz — Fri, 02 Oct 2026 14:52:24 +0000

> My problem with plugins is that I don't want to install stuff from third parties.

Then ask the model of your choice to implement the plugin for you, I created 3 this morning just for myself

New comment by 233mhz in "DeepSeek Harness Desktop for macOS and Windows"

233mhz — Fri, 02 Oct 2026 07:53:38 +0000

It sounds fancy and technical. Like when people use "orders of magnitude" six times per thread on this forum but no ever ever use it irl

New comment by 233mhz in "DeepSeek Harness Desktop for macOS and Windows"

233mhz — Fri, 02 Oct 2026 07:51:27 +0000

"china bad because china copy"

Meanwhile there is an american backdoor in your bios, cpu and router

New comment by 233mhz in "DeepSeek Harness Desktop for macOS and Windows"

233mhz — Fri, 02 Oct 2026 07:50:58 +0000

The whole thing around the model that handles system prompt, skills, agents, cache, etc. For example codex, claude code, pi, oh-my-pi, ...

New comment by 233mhz in "macOS 27 is so buggy"

233mhz — Thu, 01 Oct 2026 18:35:00 +0000

Complexity has to play a role, google chrome has more LOC than windows XP... At this point everything is a pile of piles of shit built on top of a gigantic pile of shit.

Today I ran out of ram, the "teams" desktop app was taking 2 gigs just standing there doing nothing, you can run four whole windows Xp on the same amount of ram, comfortably. My inactive chatgpt chrome tab alone was taking 900mb

New comment by 233mhz in "Clef: Open-weight decision models, and new RL fine-tuning platform"

233mhz — Thu, 01 Oct 2026 17:07:48 +0000

What's new is "smart" decision models than you can supposedly use on anything without additional training.

If you have a very narrow use case you can train a BERT based decision model on a laptop an hour if you have good data to train it on. It'll answer faster than the roundtrip to clef/jev and use <1gb memory

New comment by 233mhz in "Gemini 4 Argon"

233mhz — Thu, 01 Oct 2026 09:19:50 +0000

Benchmarks are only part of the story, most workloads don't match what you see on these.

For example sonnet is supposedly the same price as opus from medium and up, I tested it on a real world task at my day job and sonnet was a good 30-50% cheaper

New comment by 233mhz in "Tennessee inmate still alive after being administered two lethal injections"

233mhz — Thu, 01 Oct 2026 07:05:27 +0000

The problem is that you need to find an equivalent or worse psycho who don't mind chopping heads as a 9 to 5

New comment by 233mhz in "Tennessee inmate still alive after being administered two lethal injections"

233mhz — Thu, 01 Oct 2026 07:04:19 +0000

If you spent even a single day in these you'd know it's much more inhuman than death

New comment by 233mhz in "Most data centers refusing to say how much water, electricity they use"

233mhz — Wed, 30 Sep 2026 14:21:58 +0000

Now try again with local and short term impacts on the whole ecosystem instead of saying "Ackchyually water never leave the atmosphere so it's unlimited"

New comment by 233mhz in "The last time my family was replaced by technology"

233mhz — Wed, 30 Sep 2026 13:43:55 +0000

> something happened once in the past and turned ok hence you should never ever worry about other vaguely similar things ever again

That's how it sounds to me

New comment by 233mhz in "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"

233mhz — Wed, 30 Sep 2026 12:01:12 +0000

> If they really had a much more powerful model, it would make absolutely no sense to sit on it.

Makes total sense if they don't have the compute and can't serve it in an economically viable way. Also it lets you build things no one else in the world can build as fast as you until it's released

New comment by 233mhz in "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"

233mhz — Wed, 30 Sep 2026 12:00:09 +0000

> We already know OpenAI has "bel" that is MUCH better than astra and is being used internally

I mean, isn't it almost a guarantee that what we get is a gimped version of what they use internally? They probably already serve themselves next gen level models at 1k+ tps from cerebras machines hosted on perm while we get quantized astra/opus at 50tps on a good day