echion's comments

On: ML promises to be profoundly weird

[echion]

> Free Software types already do for all software

Free Software types also create software...they didn't just argue for a better license and try to regulate Sun/others to re-license their software; they wrote free (libre) versions of proprietary software and released it for free (cost), which is what counteracted the "[putting] what they make behind a wall". If you're saying "[some] LLMs should be free", I agree.

On: Ensu – Ente’s Local LLM app

[echion]

Looks excellent -- thanks; shame older intel macs don't get it (a lot of those still around)

On: Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers

[echion]

Any place we can look for you to release this?

[kir-gadjello → echion]

Yeah, my github is in the profile. Soon (tm). Feel free to follow.

On: OpenAI – How to delete your account

[echion]

Those of us whose appreciation of da Vinci's mastery are not affected by him painting the Mona Lisa with a moustache are keeping you in our thoughts.

(non-snark: your reply is clever and got a smile but I still think the GP post is overriding: no need for the distraction (c.f.: these asides) of the "S(c)am" swipe)

[mpalmer → echion]

Who's distracting who? How many people do you think noticed that letter C without your help?

I wonder how much esteem you hold for Sig. da Vinci if you equate his work with HN comments.

[echion → mpalmer]

Ad hominem much?

On: Voxtral Transcribe 2

[echion]

Same here

On: Kimi Released Kimi K2.5, Open-Source Visual SOTA-Agentic Model

[echion]

> Tiananmen square

The Tiananmen Square killings happened independent of one's "worldview".

What's an example of "the exact same thing" done to OpenAI models by western governments?

On: Dell's version of the DGX Spark fixes pain points

[echion]

> you can combine Spark with M3U, the former streaming the compute, lowering TTFT, the latter doing the token generation part

Are you doing this with vLLM, or some other model-running library/setup?

[coder543 → echion]

They're probably referencing this article: https://blog.exolabs.net/nvidia-dgx-spark/

On: Dell's version of the DGX Spark fixes pain points

[echion]

> training smart LLMs like Qwen3-Next-80B-A3B-Instruct-NVFP4

Sounds interesting; can you suggest any good discussions of this (on the web)?

On: GLM-4.7: Advancing the Coding Capability

[echion]

> with same success you can prove bias in western models.

What are some examples? (curious, as a westerner)

Are there "bias" benchmarks? (I ask, rather than just search, because: bias)

On: GLM-4.7: Advancing the Coding Capability

[echion]

> when do we stop this kind of polarization?

When the tool isn't polarized. I wouldn't use a wrench with an objectionable symbol on it.

> You don't forecast weather with image detection model

What do you do with a large language model? I think most people put language in and get language out. Plenty of people are going to look askance at statements like "the devil is really good at coding, so let's use him for that only". Do you think it should be illegal/not allowed to not hire a person because they have political beliefs you don't like?