Hacker News: alex7o

New comment by alex7o in "Saying goodbye to asm.js"

alex7o — Wed, 20 May 2026 23:31:50 +0000

I think the whole NaCL thing was able to do the ssh directly from the browser without any tunneling, but maybe I am misremembering

New comment by alex7o in "Saying Goodbye to Asm.js"

alex7o — Wed, 20 May 2026 15:56:41 +0000

I do understand why NaCL and PNaCL are undesirable and why wasm is much better, but as a student the NaCL ssh app had saved my computer science homeworks more than once, and this is something that still doesn't have an alternative although I rarely would need it nowadays.

New comment by alex7o in "Loopmaster – Livecoding Music IDE"

alex7o — Mon, 18 May 2026 21:08:37 +0000

Obligatory https://strudel.cc/ mention, same thing bit different, have made music in any of them. But I follow artists that use strudel.

New comment by alex7o in "Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model"

alex7o — Tue, 12 May 2026 22:12:14 +0000

From all the models that do toolcalls the only thing I am confused is why did you pick the worst? Or maybe they are only bad in agentic work it fine for one shot toolcalls?

New comment by alex7o in "Local AI needs to be the norm"

alex7o — Sun, 10 May 2026 20:29:14 +0000

I mean the openai API is the industry standard for allowing apps to communicate with models, llama-server has it, oMLX has it, ollama has it, vLLM has it, lmstudio as well. I don't think this is such a hard thing to do, but it requires people to set it up.

New comment by alex7o in "Local AI needs to be the norm"

alex7o — Sun, 10 May 2026 20:27:41 +0000

There is no other way than shipping your own model, because you will want an abstracted API over the inference, and you don't know what the user has installed. Also you can ship 9b fp4 model but it all just depends

New comment by alex7o in "Remind HN: Today is Mother's Day, call your moms"

alex7o — Sun, 10 May 2026 17:04:00 +0000

How is it mother day isn't that 8 march

New comment by alex7o in "Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge"

alex7o — Sun, 03 May 2026 08:09:44 +0000

I don't know about you but kimi 2.6 from the kimi subscription has been absolutely bad and useless for the past 1 week so I canceled my sub and stopped using it.

New comment by alex7o in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

alex7o — Wed, 22 Apr 2026 18:01:47 +0000

Turboquant on 4bit helps a lot as well for keeping context in vram, but int4 is definitely not lossless. But it all depends for some people this is sufficient

New comment by alex7o in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

alex7o — Wed, 22 Apr 2026 17:55:50 +0000

Because when you pay for a subscription they don't silently quantize the model a few week after release, and you can no longer get the full model running.

Otherwise no need for full fp16, int8 works 99% as well for half the mem, and the lower you go the more you start to pay for the quants. But int8 is super safe imo.

Mastra Code

alex7o — Wed, 22 Apr 2026 08:50:04 +0000

Article URL: https://code.mastra.ai/

Comments URL: https://news.ycombinator.com/item?id=47860880

Points: 2

# Comments: 0

New comment by alex7o in "Tim Cook's Impeccable Timing"

alex7o — Tue, 21 Apr 2026 15:46:51 +0000

The thing is I have never used the function keys on my laptop so that was not a problem form me, but also some of the custom functions I hard can just be mapped to fn keys so it is bit like it it us a huge loss

New comment by alex7o in "Tim Cook's Impeccable Timing"

alex7o — Tue, 21 Apr 2026 15:11:22 +0000

Fight me but I miss the touchbar, it was customizable to be super useful with better touch tool

New comment by alex7o in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

alex7o — Mon, 20 Apr 2026 21:35:42 +0000

Maybe a bit misleading. I have used in in two places.

One Is for local opencode coding and config of stuff the other is for agent-browser use and for both it did better (opus 4.6) for the thing I was testing atm. The problem with opus at the moment I tired it was overthinking and moving itself sometimes I the wrong direction (not that qwen does overthink sometimes). However sometimes less is more - maybe turning thinking down on opus would have helped me. Some people said that it is better to turn it of entirely when you start to impmenent code as it already knows what it needs to do it doesn't need more distraction.

Another example is my ghostty config I learned from queen that is has theme support - opus would always just make the theme in the main file

New comment by alex7o in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

alex7o — Mon, 20 Apr 2026 16:04:12 +0000

Ok I find it funny that people compare models and are like, opus 4.7 is SOTA and is much better etc, but I have used glm 5.1 (I assume this comes form them training on both opus and codex) for things opus couldn't do and have seen it make better code, haven't tried the qwen max series but I have seen the local 122b model do smarter more correct things based on docs than opus so yes benchmarks are one thing but reality is what the modes actually do and you should learn and have the knowledge of the real strengths that models posses. It is a tool in the end you shouldn't be saying a hammer is better then a wrench even tho both would be able to drive a nail in a piece of wood.

New comment by alex7o in "Vercel April 2026 security incident"

alex7o — Sun, 19 Apr 2026 18:59:25 +0000

Choosing an eccentric stack makes the llms do better even. Like Effect.ts or Elixir

New comment by alex7o in "Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B?"

alex7o — Fri, 17 Apr 2026 07:28:02 +0000

Think of it like that 8b model needs 8gb of vram. Also search online there is a lot of info on that

New comment by alex7o in "Claude Opus 4.7"

alex7o — Thu, 16 Apr 2026 16:52:04 +0000

Also https://github.com/rtk-ai/rtk but some people see that changing how commands output stuff can confuse some models

New comment by alex7o in "Claude Opus 4.7"

alex7o — Thu, 16 Apr 2026 16:42:06 +0000

Most likely, would be cool yes see a open source Nivel use diffusion for thinking.

New comment by alex7o in "Why I'm Building a Database Engine in C#"

alex7o — Fri, 10 Apr 2026 18:29:03 +0000

That seems great, I have seen a few similar dbs written in java that say the same thing, that when written correctly you can get the perf very close to C, but at that point you are just writing C with a different syntax. You don't win on any in the security guarantees, so at that point can we just not build everything in wasm and then we can interface it from both dotnet and the jvm?