Hacker News: andrewmunsell

New comment by andrewmunsell in "GLM-5.3 is now open-weight"

andrewmunsell — Fri, 28 Aug 2026 16:05:33 +0000

It's also now live on Ollama Cloud as of a couple minutes ago

New comment by andrewmunsell in "Claude Code is steganographically marking requests"

andrewmunsell — Tue, 30 Jun 2026 16:29:43 +0000

My guess is for distillation, they need to forward the prompt to Anthropic to get the real Anthropic model's response so they can train their own models on it

New comment by andrewmunsell in "Claude Fable 5"

andrewmunsell — Tue, 09 Jun 2026 18:06:40 +0000

Improvements in model performance aren't always strictly compute-constrained in a way that makes them reliant on Moore's Law. Open weight models-- in particular, from Chinese labs-- are optimizing model intelligence with less compute. They're "behind" frontier models by months, but as others have noted, it's possible to get Sonnet 4.5+ level performance at reduced cost, today, from open weight labs.

New comment by andrewmunsell in "Newly purchased Vizio TVs now require Walmart accounts to use smart features"

andrewmunsell — Thu, 26 Mar 2026 15:00:31 +0000

This has been a thing for years, and so much so, that there's an entire TV with a dedicated second screen that shows you ads underneath your main screen: https://www.telly.com

New comment by andrewmunsell in "US air traffic controllers start resigning as shutdown bites"

andrewmunsell — Sun, 09 Nov 2025 23:32:39 +0000

No one rich enough flying what the average person would consider a "private jet" or private plane would be flying VFR from uncontrolled airport to uncontrolled airport. The "ultra rich" are not puttering around in single-engine Cessnas

New comment by andrewmunsell in "Addendum to GPT-5 system card: GPT-5-Codex"

andrewmunsell — Mon, 15 Sep 2025 19:49:10 +0000

Yes, but I had to update the Codex CLI manually via NPM to see it. The VS Code extension auto-updated for me

New comment by andrewmunsell in "OpenAI Codex hands-on review"

andrewmunsell — Tue, 20 May 2025 17:54:49 +0000

> incorrect, its an o3 finetune.

This is Open AI's fault (and literally every AI company is guilty of the same horrid naming schemes). Codex was an old model based on GPT-3, but then they reused the same name for both their Codex CLI and this Codex tool...

I mean, just look at the updates to their own blog post, I can see why people are confused.

https://openai.com/index/openai-codex/

Edit:

Google just did it too. "Gemini Ultra" is both a model (https://deepmind.google/models/gemini/ultra/) and their new top-tier subscription plan (a la Open AI's Pro plan). Why is this so difficult?

New comment by andrewmunsell in "Void: Open-source Cursor alternative"

andrewmunsell — Fri, 09 May 2025 01:34:04 +0000

The reason I have never bothered with Claude Code (or even other agentic tools), is that I still code mostly by hand.

When I am using LLMs, I know exactly what the code should be and just am using it as a way to produce it faster (my Cursor rules are extremely extensive and focused on my personal architecture and code style, and I share them across all my personal projects), rather than producing a whole feature. When I try and use just the agent in Cursor, it always needs significant modifications and reorganization to meet my standards, even with the extensive rules I have set up.

Cursor appeals to me because those QOL features don't take away the actual code writing part, but instead augment it and get rid of some of the tedium.

New comment by andrewmunsell in "Void: Open-source Cursor alternative"

andrewmunsell — Thu, 08 May 2025 18:57:19 +0000

Given that there's a dozen agentic coding IDEs, I only use Cursor because of the few features they have like auto-identification of the next cursor location (I find myself hitting tab-tab-tab-tab a lot, it speeds up repetitive edits). Are there any other IDEs that implement these QOL features, including Void (given it touts itself specifically as a Cursor alternative)?

New comment by andrewmunsell in "ChatGPT is turning everything into Studio Ghibli art"

andrewmunsell — Sat, 29 Mar 2025 15:44:20 +0000

https://archive.is/okv6M

New comment by andrewmunsell in "Apple M5 could ditch unified memory architecture for split CPU and GPU designs"

andrewmunsell — Mon, 30 Dec 2024 21:11:59 +0000

On the Apple Edu store, it's $499 for the 16/256 and $1079 for the 32/512

New comment by andrewmunsell in "QwQ: Alibaba's O1-like reasoning LLM"

andrewmunsell — Fri, 29 Nov 2024 02:20:04 +0000

Another data point:

17.6 tokens/s on an M4 Max 40 core GPU

New comment by andrewmunsell in "M4 MacBook Pro"

andrewmunsell — Wed, 30 Oct 2024 16:45:43 +0000

Data privacy-- some stuff, like all my personal notes I use with a RAG system, just don't need to be sent to some cloud provider to be data mined and/or have AI trained on them

New comment by andrewmunsell in "Nearly all of the Google images results for "baby peacock" are AI generated"

andrewmunsell — Mon, 07 Oct 2024 16:51:21 +0000

Sellers are actually supposed to mark items as AI generated/assisted, where applicable: https://techcrunch.com/2024/07/09/etsy-new-seller-policy-202...

Whether they actually do this (and whether there's any incentive to do so), is obviously not a given

New comment by andrewmunsell in "Apple Explains iPhone 15 Pro Requirement for Apple Intelligence"

andrewmunsell — Wed, 19 Jun 2024 16:46:15 +0000

If Apple's "Private Cloud Compute" is used even on the latest devices for some tasks that are too computationally complex to be done on-device, then is there some reason (other than money) that they can't launch Apple Intelligence on all iOS 18 devices but use the cloud for all "AI" requests that would be "too slow" because of the older chips?

New comment by andrewmunsell in "Apple Intelligence for iPhone, iPad, and Mac"

andrewmunsell — Mon, 10 Jun 2024 18:53:59 +0000

From MacRumors:

> Notes can record and transcribe audio. When your recording is finished, Apple Intelligence automatically generates a summary. Recording and summaries coming to phone calls too.

So the functionality exists, maybe just not in the Voice Memos app?

New comment by andrewmunsell in "Apple announces new accessibility features, including eye tracking"

andrewmunsell — Wed, 15 May 2024 18:11:39 +0000

CarPlay is rendered by the phone itself, so it's not strictly a function of how powerful the car infotainment is. You've been able to talk to Siri since the beginning of CarPlay so additional voice control is really just an accessibility thing

New comment by andrewmunsell in "Apple introduces M4 chip"

andrewmunsell — Tue, 07 May 2024 15:38:04 +0000

My current assumption is that this has to do with whatever "AI" Apple is planning to launch at WWDC. If they launched a new iPad with an M3 that wasn't able to sufficiently run on-device LLMs or whatever new models they are going to announce in a month, it would be a bad move. The iPhones in the fall will certainly run some new chip capable of on-device models, but the iPads (being announced in the Spring just before WWDC) are slightly inconveniently timed since they have to announce the hardware before the software.

New comment by andrewmunsell in "Wi-Fi 7 certification is now underway for new routers and devices"

andrewmunsell — Mon, 08 Jan 2024 17:33:24 +0000

You appear to be right, as far as I can tell the standard itself has not been ratified

https://www.ieee802.org/11/Reports/tgbe_update.htm

https://en.wikipedia.org/wiki/IEEE_802.11be

> Development of the 802.11be amendment is ongoing, with an initial draft in March 2021, and a final version expected by early 2024

New comment by andrewmunsell in "WPA3 Enterprise 192-bit mode at home"

andrewmunsell — Fri, 05 Jan 2024 03:20:43 +0000

I was very excited by this, but I found that some of my dumber IoT devices would refuse to connect to the network if it used PPSK. If I connect them to a separate SSID I use for IoT devices with a basic WPA2 PSK, they work totally fine, but I didn't dig too much so it could also be user error