Hacker News: coder68

New comment by coder68 in "RTX 5090 and M4 MacBook Air: Can It Game?"

coder68 — Thu, 14 May 2026 16:29:14 +0000

This seems pretty useful for AI inference if it can pass Apple approval. I've wanted to use my Nvidia GPUs with a Mac Mini, this would enable it to run CUDA directly. Very cool!

New comment by coder68 in "AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights"

coder68 — Sat, 02 May 2026 17:43:05 +0000

What would be an example of a positive signal?

New comment by coder68 in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

coder68 — Mon, 20 Apr 2026 15:16:48 +0000

In fact it is appreciated that Qwen is comparing to a peer. I myself and several eng I know are trying GLM. It's legit. Definitely not the same as Codex or Opus, but cheaper and "good enough". I basically ask GLM to solve a program, walk away 10-15 minutes, and the problem is solved.

New comment by coder68 in "Why AI Sucks at Front End"

coder68 — Sun, 12 Apr 2026 14:27:12 +0000

AI is much better at front-end than me, it has really enabled me to build visual apps as a normally backend/ML guy.

New comment by coder68 in "Help Keep Thunderbird Alive"

coder68 — Thu, 09 Apr 2026 15:01:27 +0000

A bit more context would be helpful, as someone happy to donate -- what is the current situation, why the urgency? Just some more info would be good.

New comment by coder68 in "Google releases Gemma 4 open models"

coder68 — Thu, 09 Apr 2026 01:27:34 +0000

Hmm you might be able to tweak the settings further. Under llama.cpp on one RTX 6000 Pro I get ~215 tok/s generation speed. The key for me was setting min_p greater than 0. My settings:

``` #!/bin/bash

llama-server \ -hf ggml-org/gpt-oss-120b-GGUF \ -c 0 \ -np 1 \ --jinja \ --no-mmap \ --temp 1.0 \ --top-p 1.0 \ --min-p 0.001 \ --chat-template-kwargs '{"reasoning_effort": "high"}' \ --host 0.0.0.0 ```

New comment by coder68 in "Muse Spark: Scaling towards personal superintelligence"

coder68 — Wed, 08 Apr 2026 17:02:46 +0000

I have not delved into the theory yet but it seems that the smaller open-source models do this already to an extent. They have less parameters, but spend much more time/tokens reasoning, as a way to close the performance gap. If you look at "tokens per problem" on https://swe-rebench.com/ it seems to be the case at least.

New comment by coder68 in "A case study in testing with 100+ Claude agents in parallel"

coder68 — Mon, 06 Apr 2026 04:24:18 +0000

20 years is quite an optimistic timeline. Of course, we will use agents to solve the problems of agents!

New comment by coder68 in "Google releases Gemma 4 open models"

coder68 — Thu, 02 Apr 2026 19:36:37 +0000

I gave it a whirl but was unenthused. I'll try it again, but so far have not really enjoyed any of the nvidia models, though they are best in class for execution speed.

New comment by coder68 in "Google releases Gemma 4 open models"

coder68 — Thu, 02 Apr 2026 18:43:49 +0000

Are there plans to release a QAT model? Similar to what was done for Gemma 3. That would be nice to see!

New comment by coder68 in "Google releases Gemma 4 open models"

coder68 — Thu, 02 Apr 2026 18:41:12 +0000

120B would be great to have if you have it stashed away somewhere. GPT-OSS-120B still stands as one of the best (and fastest) open-weights models out there. A direct competitor in the same size range would be awesome. The closest recent release was Qwen3.5-122B-A10B.

New comment by coder68 in "How the AI Bubble Bursts"

coder68 — Mon, 30 Mar 2026 15:31:36 +0000

The good news is local models have significantly improved. If it all goes down today, you can still run e.g. Qwen 3.5 at home, and it's "good enough" for most workloads.

With a gaming GPU you can run Qwen3.5-35B-A3B. I use 122B-A10B on my local rig (1x6000 Pro), and 397B-A17B on my 2x6000 Pro server (some spillover into CPU/RAM). It's pricey now but probably within a few years it'll become very affordable.

New comment by coder68 in "Ask HN: Is anyone here also developing "perpetual AI psychosis" like Karpathy?"

coder68 — Wed, 25 Mar 2026 16:56:24 +0000

We all probably need to touch grass a bit. Our industry is really out of touch with reality right now, although the looming impact of AI is probably quite real.

New comment by coder68 in "Meta's Omnilingual MT for 1,600 Languages"

coder68 — Tue, 24 Mar 2026 20:42:34 +0000

Thanks! Super interested in LLMs for translation :D glad to see you folks doing this work.

New comment by coder68 in "LLMs predict my coffee"

coder68 — Sun, 22 Mar 2026 22:17:33 +0000

It does? There is a fast drop followed by a long decay, exponential in fact. The cooling rate is proportional to the temperature difference, so the drop is sharpest at the very beginning when the object is hottest.

New comment by coder68 in "Meta's Omnilingual MT for 1,600 Languages"

coder68 — Sun, 22 Mar 2026 20:35:12 +0000

Is there interest in benchmarking the proprietary LLMs for translation? Curious as I often use Gemini 3 Flash, but I have no idea how good it is for my language family. I prefer open models (in fact the smaller the better for offline), but it'd be useful to know how well the Big Three do.

New comment by coder68 in "US economy unexpectedly sheds 92k jobs in February"

coder68 — Fri, 06 Mar 2026 20:53:06 +0000

Even working in "tech" but not FAANG this is so true, 10 days is still the norm at many white collar businesses for your first year of employment, sometimes 15 days if they're generous.

New comment by coder68 in "US economy unexpectedly sheds 92k jobs in February"

coder68 — Fri, 06 Mar 2026 20:52:11 +0000

The tradeoff with many EU countries would be that they enjoy their leisure time a lot more and sooner than Americans. Americans make more and save more statistically, but they spend it on cars, houses, and medical care, and generally have way less free time. So I think it's a wash.

New comment by coder68 in "Nabokov's guide to foreigners learning Russian"

coder68 — Thu, 25 Dec 2025 11:37:55 +0000

As someone studying Polish, and making excellent progress, I mostly agree with your take. If you want to explore other languages, something like Spanish will get you much more mileage. Polish is difficult and the community of speakers isn't exactly warm to foreigners or people acquiring the language. On the other hand, if you truly enjoy languages and are passionate about them, I have found Polish to be really interesting and beautiful in its own way. Definitely not recommended, but still enjoyable to read/write/speak.

New comment by coder68 in "SpaCy: Industrial-Strength Natural Language Processing (NLP) in Python"

coder68 — Fri, 29 Aug 2025 03:16:33 +0000

To chime in about where I'm at -- one problem was solved with a statistical classifier, but to bootstrap another, I ended up using keywords. It took a few hours to get a reasonable solution, and it leans more towards precision than recall, but it worked quickly!