Hacker News: ac29

New comment by ac29 in "Kimi K3: Open Frontier Intelligence"

ac29 — Thu, 16 Jul 2026 22:56:06 +0000

OpenCode Go is a great deal but I recently dumped my subscription because I found myself rarely reaching for it over my Anthropic sub (I can get 40 hours of work a week out of the $20 sub and almost never hit weekly limits). Subscribed to OpenAI as my secondary and I've been really impressed with that too so far.

I expect if they add Kimi 3 to Go the limits are going to be really low since 2.7 is already one of the most limited models and 3 is much larger.

New comment by ac29 in "Kimi K3: Open Frontier Intelligence"

ac29 — Thu, 16 Jul 2026 22:46:36 +0000

You do understand that the "frontier" people are usually talking about is the cost-intelligence frontier right?

By definition there is no model that is both cheaper and as intelligent or better than another on the frontier.

New comment by ac29 in "The real prices of frontier models. Tokens * Price, right?"

ac29 — Mon, 13 Jul 2026 22:45:15 +0000

> You will see people claim Claude uses 2x to 4x the tokens of GPT.

My guess is something to this effect was in the prompt and the LLM made a point of correcting it

New comment by ac29 in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

ac29 — Sun, 12 Jul 2026 22:47:46 +0000

Try an 8 bit quant of Qwen 35B, but temper your expectations. Those Qwen 3.6 models are impressive for the size, but you need an order of magnitude more parameters to actually be useful for more than trivial work in my opinion.

New comment by ac29 in "QuadRF can spot drones and see WiFi through my wall"

ac29 — Fri, 10 Jul 2026 17:12:30 +0000

Phased array radars are export controlled in the US. It doesnt mean its illegal to build or own, but it might be illegal to sell in some cases

New comment by ac29 in "Show HN: Getting GLM 5.2 running on my slow computer"

ac29 — Fri, 10 Jul 2026 03:18:59 +0000

llama.cpp supports a wide variety of 4-bit and smaller quants and mmap's models by default, so you dont need to be able to hold the weights in memory (the OS will handle bringing them in from storage as needed)

Its cool to see this implemented in a tiny amount of code without dependencies, but does it actually bring more performance?

New comment by ac29 in "Anthropic's Method to Losing Goodwill in a Few Easy Steps"

ac29 — Mon, 06 Jul 2026 14:06:58 +0000

> So... maybe we can still use third party harnesses with Claude Code subscriptions... for now?

The way I read this is: yes, if the third party harness uses Anthropic's Agent SDK. Most of them do not, AFAIK, and are still against ToS (though maybe its not enforced for now)

New comment by ac29 in "The bottleneck might be the air in the room"

ac29 — Sat, 04 Jul 2026 21:07:24 +0000

I have a SwitchBot Meter Pro CO2 that is just temp/humidity/C02. Works well and was inexpensive ($50 or so).

New comment by ac29 in "The bottleneck might be the air in the room"

ac29 — Sat, 04 Jul 2026 20:53:26 +0000

I've got a NDIR CO2 sensor about 6 weeks into a supposed 1 year battery life, still reporting 100% battery. Power use is very low since it only fires up the CO2 sensor every 30 mins.

New comment by ac29 in "ZCode – Harness for GLM-5.2"

ac29 — Thu, 02 Jul 2026 14:06:00 +0000

Giving users ability to use apt with root privileges is pretty much game over security wise. Full root is a malicious package away

New comment by ac29 in "Kimi K2.7 Code is generally available in GitHub Copilot"

ac29 — Thu, 02 Jul 2026 13:27:14 +0000

> Anthropic just provides a subscription - which Enterprise usually doesn't want you to use because everything you're submitting through that will be trained on / becomes part of their model.

My Pro account very clearly has a toggle for "Help improve our AI models: Allow the use of your chats and coding sessions to train and improve Anthropic AI models."

New comment by ac29 in "GLM 5.2 beats Claude in our benchmarks"

ac29 — Mon, 29 Jun 2026 01:40:25 +0000

The inference providers are running batch sizes much larger than 10

New comment by ac29 in "Apple to skip high-end M6 Mac chips in favor of AI-focused M7 line"

ac29 — Fri, 26 Jun 2026 10:22:43 +0000

I'm certainly willing to believe the M1 was the most energy efficient, but your data center didnt have anything faster than a laptop?

New comment by ac29 in "Apple raises prices of MacBooks, iPads"

ac29 — Thu, 25 Jun 2026 18:16:42 +0000

I did my first ESP32 project recently and was amazed you can get a system that starts up Micropython, then a Wifi AP, DNS, and Web Server in a second or two total and uses less than 512kB RAM. And thats with a high level programming language.

New comment by ac29 in "IBM debuts sub-1 nanometer chip technology"

ac29 — Thu, 25 Jun 2026 17:58:45 +0000

> IBM no longer owns any fabs

Per IBM: "IBM Research at Albany [...] includes more than 100,000 square feet of semiconductor fabrication space"

I guess that is technically a R&D fab not a production one, but they definitely have in house fabrication capability

New comment by ac29 in "Crypto in 2026: Oh, This Is the Bad Place"

ac29 — Tue, 23 Jun 2026 14:45:32 +0000

Most real financial transactions need to start and end in fiat though, and that's where the costs are

New comment by ac29 in "TerraPower in deal with Meta for eight Natrium 345 MW nuclear plants"

ac29 — Thu, 18 Jun 2026 18:45:56 +0000

A change in regulations is not a meritless argument, it's useful information

New comment by ac29 in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

ac29 — Wed, 17 Jun 2026 14:17:01 +0000

You could subscribe to Anthropic/OpenAI for the rest of your life for the cost it would take to host GLM5.2 locally - you need 1.5TB of VRAM just for the weights

New comment by ac29 in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

ac29 — Tue, 16 Jun 2026 14:44:57 +0000

> I'd rather use Sonnet than Qwen

I get this, though the pace of Chinese releases is relentless. Qwen3.7 Plus/Max (closed variants) feel notably better than Qwen3.6, and Minimax M3 is a big jump from 2.7 in capability as well. Both of these families had their previous major release less than 90 days ago.

Anthropic must have Sonnet 5 either waiting or cooking though, they said smaller and larger models than Opus were coming and we already briefly had the larger model.

New comment by ac29 in "Apple Foundation Models"

ac29 — Mon, 15 Jun 2026 13:43:54 +0000

If you use uv, python apps use a shared cache which helps a lot.