Hacker News Reader

Cool.

I'm using gdrive under Linux and it's a pain. Takes 10 seconds to open a folder.

I have a proton subscription and would love to move my stuff there if it works reasonably faster under Linux than gdrive

k__on Telegram Desktop vulnerability allowed any user's file to be stolen

They are restructuring their companies regularly and keep the core company small.

k__on Why isn't the industry freaking out about DeepSeek 4.1 Flash?

DeepSeek themselves said 4.1 Flash is better than their current Pro version.

k__on The 15-year search for a band that charted once and vanished

Loved Spotify when it was good.

I found so many bands east Europe, all written in Cyrillic, so I couldn't have searched for them easily.

Before that I used Soulseek for Japanese bands.

k__on Fitts's law: why the menu bar is at the top

Isn't desktop software maximized most of the time anyway?

k__on Our approach to EU text provenance rules

Yes, thank you

k__on Our approach to EU text provenance rules

And that's part of inference engine or model?

k__on Our approach to EU text provenance rules

Is watermarking part of a model architecture or is it something added by the inference engine?

k__on Your body of work thinks back at you

I think, it's sad that we live in a society that doesn't help those addicts.

k__on Your body of work thinks back at you

The dysfunction needs more empathy.

k__on Agents don't need memory, they need documentation

What's with this vector database obsession?

k__on ADHD, autism or complex trauma? [pdf]

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

k__on Pi 1.0

"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).

k__on Pi.dev: You Said No MCP

What would you say is a good harness with subagents?

k__on Livenerf: Has Opus 5.5 been nerfed yet?

Another reason not to use proprietary models for your products

k__on Jeeves. Reasoning improves Jev-like decision models

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.

k__on Jeeves. Reasoning improves Jev-like decision models

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.

k__on Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

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

k__on Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

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

k__on Jeff – Jev-compatible 0.8B decision models, trained at home, ~30 ms

Von 1.2 had a better Doom score :D

https://github.com/wfzyx/von

k__on 13 Months Sober (2025)

Yeah

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

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

k__on 13 Months Sober (2025)

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.

k__on Ember-1

Half the tokens can also mean quicker task completion

k__on What would a serious AI product look like?

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.

k__on Ember-1

Vertical integration.

k__on Ember-1

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

k__on Ember-1

If they can keep up.

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

k__on Turning GLM-5.3-Flash into a Jev-like decision model

Is it non-autoregressive?

k__on Ollaya – Ollama for open-source, Jev-style decision models

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

k__on Ollaya – Ollama for open-source, Jev-style decision models

But aren't BERTs tiny compared to a LLM and can be trained cheaply with the help of an LLM?