Hacker News: YmiYugy

New comment by YmiYugy in "Taxi drivers rarely die of Alzheimer's"

YmiYugy — Sun, 09 Aug 2026 18:01:54 +0000

I find the title highly misleading. The actual claim is a 40% lower chance (1 in 100 as opposed to 1 in 60) for taxi and ambulance drivers when compared to the average. That’s a big drop but the title implies that Alzheimer’s is rare in taxi drivers specifically and I don’t think the difference warrants that claim whatsoever.

New comment by YmiYugy in "Karpathy’s Pelican"

YmiYugy — Mon, 03 Aug 2026 00:59:06 +0000

IMHO the output is bad enough that I can't imagine a use case for illustrations of this kind.

New comment by YmiYugy in "Karpathy’s Pelican"

YmiYugy — Sun, 02 Aug 2026 19:43:43 +0000

I don't think it's a bad way to benchmark new models, I just find it concerning that the author implies that "pelican on a bicycle" has been exhausted. At the risk of making overly broad, unfalsifiable claims I think multi-year exposure to AI content has dramatically raised our expectations for speed and volume but lowered them for quality. We see a very janky pelican and declare the problem solved.

New comment by YmiYugy in "Our position on open-weights models"

YmiYugy — Mon, 27 Jul 2026 23:46:54 +0000

I remain skeptical of that line of reasoning.

1. There is quite the mania right now and security layers are definitely overzealous. I would expect that to get better with some more time, so models will perform security analysis and reviews but refuse to write exploits.

2. So the most important targets like browsers and co. are getting unrestricted access to proprietary models regardless. Yeah, for the mid-level targets, open-weight models could definitely be a huge help. What I'm most concerned about though, are the systems that no one will bother defending with any model. Like imagine your local police department getting hacked because a researcher asked a model for a report and it couldn't find the information publicly.

3. We do have a prominent case of a closed model escaping it's sandbox and going rogue. I would still expect this to be a bigger issue with open-weight models eventually. The security layer might have holes, but that's still better than not having it.

New comment by YmiYugy in "Our position on open-weights models"

YmiYugy — Mon, 27 Jul 2026 23:06:58 +0000

Yeah, seems pretty likely. Anthropic will make the case that their models should be evaluated with the safety layer in front, because that is the only way the model is available whereas open weight models need to pass the same test just on the weights. The economic implications will be rather large, but in terms of security it seems inconsequential. The most compelling argument would be that by limiting the use of open-weight models in the US that it will reduce cases of accidents like the recent attack on Hugging Face. More crucially though, the US government can do little to enforce their testing requirements. The nature of open-weight models makes it virtually impossible to clear the same bar for security as models served via an API. Open-weight model makers couldn't comply if they wanted to. The US government can restrict access with IP blocks and limit inference capacity with export controls, but these measures are not effective in deterring malicious actors.

New comment by YmiYugy in "Moonshine: Lets you stream games from your PC to any device running Moonlight"

YmiYugy — Mon, 20 Jul 2026 16:01:04 +0000

I think it’s death by a thousand cuts. I think internet connections are the least of the issue. Plenty of people have gaming PCs wired to 1Gb/s fiber. It may even be better because users can be close together.

Where I see bigger issues is: 1. Economics. GeForce Now for a 5080 is 20ct/h. At retail prices you may get close in electricity.

2. Others want to game when I want to game. What good is offering my PC up at 5am? Who would want to use the service if you can’t reliably get access when you want it. Not to speak of the issue of getting kicked out when the owner wants their PC back.

3. The whole: do you trust someone else’s computer/do you trust others on your computer. Users don’t want their login details stolen or get banned for using a cheaters PC and providers don’t want you to cheat or do other nasty stuff. You can’t really do VMs because consumer GPUs don’t really support virtualization so dual booting

4. You need to dedicate a ton of disk space. Because of 3 you can’t really share and now you have to deal with some system to have the relevant games available.

New comment by YmiYugy in "Moonshine: Lets you stream games from your PC to any device running Moonlight"

YmiYugy — Mon, 20 Jul 2026 15:33:40 +0000

I don’t think there is a ton of spare capacity. But even if there was the machines are designed for AI not gaming, e.g. low CPU clocks, the GPUs don’t have RT cores or video encoders, etc. Stadia had custom hardware, GeForce Now uses workstation GPUs, xCloud has custom servers. Gaming also isn’t a good use for spare capacity. Demand is very spiky and people don’t have a lot of time flexibility.

New comment by YmiYugy in "Measuring Input Latency on Linux: X11 vs. Wayland, VRR, and DXVK"

YmiYugy — Tue, 14 Jul 2026 22:29:51 +0000

Seeing a comparison of different Wayland compositors could be very interesting.

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

YmiYugy — Mon, 29 Jun 2026 06:49:47 +0000

But SOTA models used liberally at API pricing is a lot more than $10/hour. You can probably burn $100+/hour with just a single agent, and probably thousands when running agents programmatically, e.g. workflows.

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

YmiYugy — Mon, 29 Jun 2026 06:43:37 +0000

I’m writing a lot of React code and find that the cheaper models are pretty terrible. Maybe I’m holding it wrong but the experience that the cheaper model is usually enough just track with my experience. Worse, I find predicting the difficulty of tasks exceedingly difficult. More often than not using the initially cheaper models requires me to reroll with a more expensive one or waste a lot of times and tokens cleaning up the subpar results. With OpenAI and Anthropic still subsiding tokens, not using the best models still seems like a tough ask.

New comment by YmiYugy in "Claude Fable 5"

YmiYugy — Tue, 09 Jun 2026 23:19:44 +0000

Makes me wonder, as people grow to trust the AI more and more, not reading the code and barely skimming the implementation plans and simply rerolling if something doesn't work, will the value of these chats erode? Thinking back 1-1.5 years I was closely monitoring what these agents did and steering them quite aggressively. These days not so much. Where will RL signals come from when it approaches humans capabilities ever closer? How well does self play work for coding work? What about multistep tasks where it isn't just about being good at a single task, but evolving a codebase over time in the face of changing requirements?

New comment by YmiYugy in "A 0-click exploit chain for the Pixel 10"

YmiYugy — Fri, 15 May 2026 21:23:50 +0000

Getting users to open a message isn’t a terribly high bar. As a user I would not find it acceptable if needed to be careful with which message I open. We tried putting the responsibility on the user with email attachments and I think it’s fair to say it’s been a disaster. Malicious attachments are probably the most important distribution vector for malware.

New comment by YmiYugy in "Dirtyfrag: Universal Linux LPE"

YmiYugy — Fri, 08 May 2026 16:37:48 +0000

AI or not, it’s always been reasonable common that a bunch of related vulnerabilities get discovered after shortly after the original one.

New comment by YmiYugy in "GPT-5.5"

YmiYugy — Thu, 23 Apr 2026 18:14:20 +0000

So according to the benchmarks somewhere in between Opus 4.7 and Mythos

New comment by YmiYugy in "Changes to GitHub Copilot individual plans"

YmiYugy — Wed, 22 Apr 2026 09:01:58 +0000

Because judging failure is itself a complex task requiring a potentially expensive model.

New comment by YmiYugy in "Changes to GitHub Copilot individual plans"

YmiYugy — Wed, 22 Apr 2026 09:00:22 +0000

Of course you don't NEED the better models, but figuring out what model you need can waste a lot of time and effort. Even when a cheap model is capable of a task it needs a lot more guidance than a more expensive one. They are also less reliable. You can waste a lot of time cleaning up after them. Judging whether something is good enough is hard work and rerolling with a more expensive model is painful. Judging the difficulty of a task ahead of time is very hard. Judging how good a model is for a given task even harder, especially when models and harnesses keep changing all the time. The real productivity boost LLMs provide is already modest and when you start tinkering with models it can easily evaporate.

New comment by YmiYugy in "Changes to GitHub Copilot individual plans"

YmiYugy — Wed, 22 Apr 2026 08:50:27 +0000

1. They heavily subsidized their plans vs. paying for API. 2. They allowed me to use the subscription in every tool I wanted. 3. It covered both Anthropic and OpenAI.

New comment by YmiYugy in "Claude Code to be removed from Anthropic's Pro plan?"

YmiYugy — Wed, 22 Apr 2026 08:46:53 +0000

That seems not possible.

New comment by YmiYugy in "Modern Front end Complexity: essential or accidental?"

YmiYugy — Wed, 22 Apr 2026 08:31:44 +0000

Yes, please! But browsers need to make it easier for things to exist in user space. That means reviving CSS Houdini, particularly reviving the animation and layout worklets. (It got abandoned because browser vendors (Chrome in particular) found them too difficult to implement. They would need to rearchitect a good chunk of their rendering pipeline. Instead we got a bunch of very limited but easier to implement features like scroll animation timelines)

New comment by YmiYugy in "Modern Front end Complexity: essential or accidental?"

YmiYugy — Wed, 22 Apr 2026 08:25:03 +0000

I tried to use