Hacker News: kanemcgrath

New comment by kanemcgrath in "GitHub Copilot is moving to usage-based billing"

kanemcgrath — Tue, 28 Apr 2026 06:39:11 +0000

So far I have done coding projects only, but I have some ideas for some non-coding agent projects in the future, so I'll give Gemma another shot

New comment by kanemcgrath in "GitHub Copilot is moving to usage-based billing"

kanemcgrath — Mon, 27 Apr 2026 19:16:29 +0000

I did, but in almost everything I tried even qwen3.5 was better, and 3.6 was a huge step up.

New comment by kanemcgrath in "GitHub Copilot is moving to usage-based billing"

kanemcgrath — Mon, 27 Apr 2026 18:24:57 +0000

I do love using local models when I can, but qwen-35B is the best model I can run, and while its an insanely good local model, it does not compare to the big ones.

New comment by kanemcgrath in "GitHub Copilot is moving to usage-based billing"

kanemcgrath — Mon, 27 Apr 2026 18:14:35 +0000

I liked copilot because I didn't have to think about tokens. I get hung up when having to think about the price of things, and its hard to think about the project at the same time I got to think about token usage like a gas bill. The usage system had its own issues, but having a set amount of requests was a very comfortable way to use a paid AI service.

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

kanemcgrath — Fri, 17 Apr 2026 20:12:08 +0000

I haven't ran 27b that much because it only runs at like 2 tokens/sec on my computer.

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

kanemcgrath — Fri, 17 Apr 2026 00:24:49 +0000

I would say byteshape is smaller and faster, I can’t really notice a quality difference. But I haven’t used it as much as I only started using it a few days ago.

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

kanemcgrath — Thu, 16 Apr 2026 23:42:18 +0000

Now that I have tried out on a few tasks, Qwen3.6 is a huge jump in capability. It can make improvements to a project that qwen3.5 always struggled with.

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

kanemcgrath — Thu, 16 Apr 2026 20:07:09 +0000

I have been using Qwen3.5-35B-A3B a lot in local testing, and it is by far the most capable model that could fit on my machine. I think quantization technology has really upped its game around these models, and there were two quants that blew me away

Mudler APEX-I-Quality. then later I tried Byteshape Q3_K_S-3.40bpw

Both made claims that seemed too good to be true, but I couldn't find any traces of lobotomization doing long agent coding loops. with the byteshape quant I am up to 40+ t/s which is a speed that makes agents much more pleasant. On an rtx 3060 12GB and 32GB of system ram, I went from slamming all my available memory to having like 14GB to spare.

New comment by kanemcgrath in "Rare concert recordings are landing on the Internet Archive"

kanemcgrath — Tue, 14 Apr 2026 20:22:46 +0000

since they have been doing orchestral performances, getting to hear the orchestral versions of their old songs has been amazing.

New comment by kanemcgrath in "Nvidia's DLSS 5 uses generative AI to boost photorealism in video games"

kanemcgrath — Tue, 17 Mar 2026 20:49:15 +0000

I don't like the Netflix CGI slop movie style filter look it gives everything. But that is a more general trend in tv and movies that I just can't stand.

I do think this will eventually be a major part of the graphics pipeline, but I hope it will be limited and masked to things like hair, which is almost impossible to get right in real-time rendering.

New comment by kanemcgrath in "Is legal the same as legitimate: AI reimplementation and the erosion of copyleft"

kanemcgrath — Mon, 09 Mar 2026 21:25:15 +0000

without discussing copyright, I don't believe any of this is copied. Which I think should be the argument that actually matters.

I downloaded both 6.0 and 7.0 and based on only a light comparison of a few key files, nothing would suggest to me that 7.0 was copied from 6.0, especially for a 41x faster implementation. It is a lot more organized and readable in my armature opinion, and the code is about 1/10th the size.

New comment by kanemcgrath in "Phi-4-reasoning-vision and the lessons of training a multimodal reasoning model"

kanemcgrath — Sun, 08 Mar 2026 23:30:03 +0000

Small local models are the only thing that still have that magic feeling to me. While large models are still useful and impressive, it makes more sense that they are happening on a giant super computer in a datacenter somewhere. But all the intelligence and capability that can run on my mid level gaming PC is astonishing to me.

New comment by kanemcgrath in "LLMs can unmask pseudonymous users at scale with surprising accuracy"

kanemcgrath — Wed, 04 Mar 2026 07:10:25 +0000

Anonymous account unmasking represents a new threat to anonymity. not just this technique with llms, but the earlier text similarity one.

But I think it would be generally easier to counter in the same way.

Use an llm or heuristics to pose as someone else.

not only do you erase your traces, you add false positives in to the system which reduces the overall effectiveness of these techniques in the future. A bit of poisoning the well.

I hope eventually an easy to use tool, with maybe a small local llm, can make it easy enough to do this, so that any future deanonymization attacks would be too untrustworthy to rely on

New comment by kanemcgrath in "enclose.horse"

kanemcgrath — Tue, 06 Jan 2026 07:33:25 +0000

I am curious on how you would algorithmically find the optimal solution for this kind of problem for much bigger grids. I wanted to do some seed finding in Factorio for the same exact problem using the generated map images, but never found a good solution that was fast enough.

New comment by kanemcgrath in "Satellites reveal heat leaking from largest US cryptocurrency mining center"

kanemcgrath — Tue, 23 Dec 2025 01:12:17 +0000

I always wondered if anybody has calculated how much of our global heating could be attributed, if any at all, to every electronic device, server, and engine outputting heat as a byproduct.

New comment by kanemcgrath in "4.3M Browsers Infected: Inside ShadyPanda's 7-Year Malware Campaign"

kanemcgrath — Wed, 03 Dec 2025 01:39:58 +0000

I made a list of the extension names here https://pastebin.com/eXb9GRjK

its mostly Homepage Wallpapers

New comment by kanemcgrath in "Copyparty, the FOSS file server [video]"

kanemcgrath — Wed, 26 Nov 2025 09:11:22 +0000

I have been using copyparty since the last hn thread on it months ago. It is a masterpiece of "Just Works" Technology.

New comment by kanemcgrath in "CDC File Transfer"

kanemcgrath — Wed, 01 Oct 2025 03:42:24 +0000

for self-hosted game streaming you can use moonlight + sunshine, they work really well in my experience.

New comment by kanemcgrath in "The AI-Scraping Free-for-All Is Coming to an End"

kanemcgrath — Mon, 15 Sep 2025 11:03:00 +0000

Not sure if its still an issue, but companies were buying popular web extensions, then auto updating malware/spyware into them. I haven't heard much about this in a while, but I think chrome still forces auto updates for extensions, so I would expect this to be the biggest vector for scraping walled data now.

New comment by kanemcgrath in "FFmpeg 8.0 adds Whisper support"

kanemcgrath — Wed, 13 Aug 2025 20:41:45 +0000

Subtitle edit is great, and their subtitle library libse was exactly what I needed for a project I did.