Hacker News: k__

New comment by k__ in "ADHD, autism or complex trauma? [pdf]"

k__ — Sat, 03 Oct 2026 19:19:42 +0000

The main issue with undiagnosed ADHD is, that people assume they can solve your issues with ideas don't work for people with ADHD.

So, your life is sprinkled with unhelpful people that mean well but think you're just not listening to them.

And you yourself think, your too dumb or lazy or whatever to get things done consistently.

The you find out it's ADHD and you learn different methods to get things done. Which is nice.

But it's also very sad if that happens years after childhood. Because you realise, you might had a more successful life if you knew earlier

New comment by k__ in "Pi 1.0"

k__ — Fri, 02 Oct 2026 10:16:10 +0000

"Terse output is a design decision in 3code; pi's chattier reply style is a design decision in pi."

Can you elaborate?

What are the decisions that lead to this difference and what are their pros and cons?

I noticed Pi being chatty, but I assumes this was a model issue (DS4.1F).

New comment by k__ in "Pi.dev: You Said No MCP"

k__ — Wed, 30 Sep 2026 11:08:00 +0000

What would you say is a good harness with subagents?

New comment by k__ in "Livenerf: Has Opus 5.5 been nerfed yet?"

k__ — Wed, 30 Sep 2026 10:11:08 +0000

Another reason not to use proprietary models for your products

New comment by k__ in "Jeeves. Reasoning improves Jev-like decision models"

k__ — Tue, 29 Sep 2026 14:25:51 +0000

Not entirely.

I think, it's a bit much to call this "no hallucinations".

Technically true, but in practice you could still choose the wrong result or the probabilities can be off.

New comment by k__ in "Jeeves. Reasoning improves Jev-like decision models"

k__ — Tue, 29 Sep 2026 12:26:16 +0000

The whole "no hallucinations" premise is based on that.

Like, yeah, you don't hallucinate, but only because you force the user to decide in the end.

The System One models ecosystem

k__ — Tue, 29 Sep 2026 11:23:20 +0000

Article URL: https://systemonemodels.tech

Comments URL: https://news.ycombinator.com/item?id=49891378

Points: 1

# Comments: 0

New comment by k__ in "Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms"

k__ — Mon, 28 Sep 2026 22:42:41 +0000

Then again, it's only a very small number and fixed set of tokens for the output.

New comment by k__ in "Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms"

k__ — Mon, 28 Sep 2026 22:02:27 +0000

No need, as that functionality can run locally no problem.

New comment by k__ in "Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms"

k__ — Mon, 28 Sep 2026 21:59:28 +0000

Von 1.2 had a better Doom score :D

https://github.com/wfzyx/von

New comment by k__ in "13 Months Sober (2025)"

k__ — Mon, 28 Sep 2026 19:14:59 +0000

Yeah

None of my grand parents made it over 65, all of them heavy drinkers.

So, I'd probably have that going for me.

New comment by k__ in "13 Months Sober (2025)"

k__ — Mon, 28 Sep 2026 18:07:54 +0000

I'm always a bit disappointed when I look at the effects of staying sober.

All these people writing about how they turned their life around, sleeping better, thinking clearer, getting more healthy, etc.

I stopped drinking 3 or 4 years ago and I don't feel any better for it.

However, I only drank like one or two nights a month, when going on a party, so most of my life I was sober anyway.

The only thing I noticed is that I'm now more awkward in social situations. I mean, sure, I might be healthier than before, but I don't have any numbers for that. It's just a thing I assume to be true.

New comment by k__ in "Ember-1"

k__ — Mon, 28 Sep 2026 16:31:54 +0000

Half the tokens can also mean quicker task completion

New comment by k__ in "What would a serious AI product look like?"

k__ — Mon, 28 Sep 2026 16:05:17 +0000

An AI product should probably start with knowing what model (e.g., arch, version, quant, etc.) you're actually using. Opaque providers make that quite hard.

People are constantly complaining about GPT/Claude constantly changing under their apps without notice.

New comment by k__ in "Ember-1"

k__ — Sun, 27 Sep 2026 21:18:50 +0000

Vertical integration.

New comment by k__ in "Ember-1"

k__ — Sun, 27 Sep 2026 21:17:23 +0000

With DeepSeek's pricing, no other value prop has been great.

New comment by k__ in "Ember-1"

k__ — Sun, 27 Sep 2026 19:04:57 +0000

If they can keep up.

The lock-in is less pronounced as it is with AWS or MS.

New comment by k__ in "Turning GLM-5.3-Flash into a Jev-like decision model"

k__ — Sun, 27 Sep 2026 14:11:37 +0000

Is it non-autoregressive?

New comment by k__ in "Ollaya – Ollama for open-source, Jev-style decision models"

k__ — Sat, 26 Sep 2026 22:17:17 +0000

Can any model give you a reasonably correct answer on that amount of data?

Von, an Open-Source Jev Alternative

k__ — Sat, 26 Sep 2026 17:37:39 +0000

Article URL: https://github.com/wfzyx/von

Comments URL: https://news.ycombinator.com/item?id=49858763

Points: 2

# Comments: 0