Hacker News: jwitthuhn

New comment by jwitthuhn in "Is AI Profitable Yet?"

jwitthuhn — Sat, 23 May 2026 05:33:48 +0000

For immediate revenue yes, but if you want advertisers to keep coming back you need to give them a good conversion rate.

New comment by jwitthuhn in "Colorado Amended SB051 (Age Verification Bill) to Exclude Open Source Projects"

jwitthuhn — Thu, 21 May 2026 02:50:57 +0000

It is very fortunate for us that the authors were kind enough to demonstrate this has nothing to do with safety by adding this exemption.

New comment by jwitthuhn in "Can someone please explain whether Cloudflare blackmailed Canonical?"

jwitthuhn — Mon, 11 May 2026 19:00:02 +0000

"Renting attack capacity from [cloudflare]" is inaccurate as I understand things. That group hosts their site behind cloudflare but I have not seen anyone claim that cloudflare's infra is used for the attacks.

This whole article seems conflate hosting an informational site run by the attackers and hosting the attack itself.

New comment by jwitthuhn in "Metal Gear Solid 2's source code has been leaked on 4chan"

jwitthuhn — Sun, 03 May 2026 18:28:06 +0000

I need scissors, 61!

New comment by jwitthuhn in "China blocks Meta's acquisition of AI startup Manus"

jwitthuhn — Mon, 27 Apr 2026 23:10:51 +0000

Could you cite the specific law that makes it illegal for someone to export their thoughts?

New comment by jwitthuhn in "I cancelled Claude: Token issues, declining quality, and poor support"

jwitthuhn — Fri, 24 Apr 2026 22:30:07 +0000

The checkboxes inform the model as well as the user, and you can observe this yourself. For example in a C++ project with MyClass defined in MyClass.cpp/h:

I ask the model to rename MyClass to MyNewClass. It will generate a checklist like:

- Rename references in all source files

- Rename source/header files

- Update build files to point at new source files

Then it will do those things in that order.

Now you can re-run it but inject the start of the model's response with the order changed in that list. It will follow the new order. The list plainly provides real information that influences future predictions and isn't just a facade for the user.

New comment by jwitthuhn in "Kernel code removals driven by LLM-created security reports"

jwitthuhn — Wed, 22 Apr 2026 20:02:17 +0000

If the LLMs run by these people are turning up real bugs then their confidence in touching kernel code seems pretty earned, imo.

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

jwitthuhn — Mon, 20 Apr 2026 18:17:35 +0000

I've been using qwen-code (the software, not to be confused with Qwen Code the service or Qwen Coder the model) which is a fork of gemini-cli and the tool use with Qwen models at least has been great.

New comment by jwitthuhn in "Game devs explain the tricks involved with letting you pause a game"

jwitthuhn — Sun, 19 Apr 2026 20:04:16 +0000

My favorite as a kid was also in a Zelda game.

In the original (and maybe also DX) release of Link's Awakening, the game uses a top-down view with the world split up into tiles. Walking of the left side of a screen makes you end up on the right side of the next screen over.

What you could do is pause at the right frame on the screen transition, and you would end up on the new screen but link's position would not change. So you walk off the left side of a screen and end up on the left side of the new screen. Lots of fun to be had with skipping important stuff with that.

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

jwitthuhn — Fri, 17 Apr 2026 11:26:05 +0000

128GB on a mac with unified memory. The model itself takes something like 110 of that and then I have ~16 left over to hold a reasonably sized context and 2 for the OS.

I do have a dedicated machine for it though because I can't run an IDE at the same time as that model.

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

jwitthuhn — Thu, 16 Apr 2026 18:08:27 +0000

I've been largely using Qwen3.5-122b at 6 bit quant locally for some c++/go/python dev lately because it is quite capable as long as I can give it pretty specific asks within the codebase and it will produce code that needs minimal massaging to fit into the project.

I do have a $20 claude sub I can fall back to for anything qwen struggles with, but with 3.5 I have been very pleased with the results.

New comment by jwitthuhn in "Anthropic downgraded cache TTL on March 6th"

jwitthuhn — Mon, 13 Apr 2026 06:40:54 +0000

It only potentially saves money for people on API pricing, it exhausts tokens faster with no benefit for users on the Claude Code subscription. Those users had their cache TTL reduced from 1 hour to 5 minutes and are saving no money because they were not paying based on the cache time in the first place.

New comment by jwitthuhn in "An update on Steam / GOG changes for OpenTTD"

jwitthuhn — Thu, 19 Mar 2026 19:11:25 +0000

So they were not "pressured" but Atari contacted them and they proceeded to make this decision based because they "needed to balance Atari’s commercial interests".

That sound indistinguishable from being pressured.

New comment by jwitthuhn in "Illinois Introducing Operating System Account Age Bill"

jwitthuhn — Tue, 17 Mar 2026 18:49:00 +0000

Why should an OS demand personal information from its users? It creates an unnecessary risk that the information will be leaked.

New comment by jwitthuhn in "California's new bill requires DOJ-approved 3D printers that report themselves"

jwitthuhn — Thu, 19 Feb 2026 20:23:07 +0000

In the US there is a certain class of politician that considers poor people being able to exercise their rights a problem that needs to be solved.

New comment by jwitthuhn in "Janet Jackson had the power to crash laptop computers (2022)"

jwitthuhn — Sat, 27 Dec 2025 19:41:48 +0000

The important distinction here is that CD-ROMs can store data indefinitely, but CD-Rs and CD-RWs can not.

New comment by jwitthuhn in "Quake's Player Speed (2017)"

jwitthuhn — Thu, 25 Dec 2025 05:11:20 +0000

PVS by my understanding will only ever over-count visible polys.

It is essentially a set of all polygons that are visible from any point inside a fixed volume, but the camera only exists at a single point inside that volume so there will probably be some polys that the camera has no LOS (though I suspect these would still be 'rendered') to and a bunch that are out of the view frustum which will not be rendered.

edit: To observe this you can also load any HL1 engine game, run `r_speeds 1` in the console, then it will show you how many world polys are currently being drawn in the corner of your screen, which is probably the count referenced by John Romero here.

New comment by jwitthuhn in "Lua 5.5"

jwitthuhn — Wed, 24 Dec 2025 20:57:14 +0000

The most recent integration I've seen is is OpenMW, which is an open source re-implementation of the Morrowind game engine. Basically it is built on the assumption that people are going to make mods that do a ridiculous amount of number-crunching in lua so any small improvement to performance is welcome.

New comment by jwitthuhn in "GLM-4.7: Advancing the Coding Capability"

jwitthuhn — Tue, 23 Dec 2025 02:16:15 +0000

At 4 bits that model won't fit into 128GB so you're spilling over into swap which kills performance. I've gotten great results out of glm-4.5-air which is 4.5 distilled down to 110B params which can fit nicely at 8 bits or maybe 6 if you want a little more ram left over.

New comment by jwitthuhn in "The Illustrated Transformer"

jwitthuhn — Mon, 22 Dec 2025 22:21:25 +0000

If you have 20 hours to spare I highly recommend this youtube playlist from Andrej Karpathy https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxb...

It starts with the fundamentals of how backpropagation works then advances to building a few simple models and ends with building a GPT-2 clone. It won't taech you everything about AI models but it gives you a solid foundation for branching out.