Hacker News: iib

New comment by iib in "Time to talk about my writerdeck"

iib — Sat, 23 May 2026 20:26:55 +0000

If anyone wants to try this without the intricate setup, if you have a linux system, you most probably can just press Ctrl+Alt+F3 and drop into a tty console directly. To return, you have to press Ctrl+Alt+F1 or Ctrl+Alt+F2. You also have multiple consoles, up until F12 probably.

I used to use this a lot when trying for a less distracting desktop, just like in the original post.

New comment by iib in "Usage-based pricing killing your vibe, here's how to roll your own local AI"

iib — Mon, 04 May 2026 20:21:49 +0000

Doesn't llama.cpp (or similar) have to evict the kv cache for this, so that performance is degraded when running multiple sessions? Or how do you load a model in memory and then use it in multiple sessions? I am still learning this stuff

New comment by iib in "OpenWarp"

iib — Fri, 01 May 2026 12:58:43 +0000

How do you use `pi` to ssh? I use `oh-my-pi`, and tried the `/ssh` command, but I couldn't get it to work. Then I saw a suggestion somewhere to just run `!ssh` to place things into the agent's context.

Is there a way to use it like "The current directory is at `ssh server`" and have the agent work from there?

New comment by iib in "I Got Sick of Remembering Port Numbers"

iib — Fri, 01 May 2026 09:55:24 +0000

I am very out of the loop. What is wrong with TP Link? What are the risks with it?

New comment by iib in "Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7"

iib — Thu, 16 Apr 2026 19:11:58 +0000

This is about the newly release Qwen3.6. Just wanted to make sure you got that correctly.

New comment by iib in "The local LLM ecosystem doesn’t need Ollama"

iib — Thu, 16 Apr 2026 08:22:23 +0000

Has anybody figured some of the best flags to compile llama.cpp for rocm? I'm using the framework desktop and the Vulkan backend, because it was easier to compile out of the box, but I feel there's large peformance gains on the table by swtiching to rocm. Not sure if installing with brew on ubuntu would be easier.

New comment by iib in "I won't download your app. The web version is a-ok"

iib — Mon, 06 Apr 2026 19:39:28 +0000

Or add your real name to photos of you stored in Google Photos.

New comment by iib in "The Cognitive Dark Forest"

iib — Mon, 30 Mar 2026 12:42:58 +0000

If by the spirit, you only mean the bazaar model, then yes. But it's in the original spirit of free software. GNU preferred to keep the development somewhat contained, even so many years ago.

New comment by iib in "Show HN: uBlock filter list to blur all Instagram Reels"

iib — Mon, 02 Mar 2026 21:21:03 +0000

It's sticky on the web though:

https://www.instagram.com/?variant=following

New comment by iib in "Pandoc in the Browser with WASM"

iib — Fri, 13 Feb 2026 00:06:01 +0000

This is really nice to know. I remember trying to compile pandoc to Wasm after finding out that ghc had Wasm support, hitting all kinds of problems and then realising that there was no real way to post an issue to Haskell's gitlab repo without being pre-approved.

I guess now with LLMs, this makes more sense than ever, but it was a frustrating experience.

New comment by iib in "Billing can be bypassed using a combo of subagents with an agent definition"

iib — Sun, 08 Feb 2026 17:16:14 +0000

Some were already that and even more, because of other reasons. The Cathedral model, described in "The Cathedral and the Bazaar".

New comment by iib in "Talking to LLMs has improved my thinking"

iib — Fri, 23 Jan 2026 06:18:48 +0000

I found Geoffrey Hinton's hypothesis of LLMs interesting in this regard. They have to compress the world knowledge into a few billion parameters, much denser than the human brain, so they have to be very good at analogies, in order to obtain that compression.

New comment by iib in "Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant"

iib — Thu, 22 Jan 2026 10:29:42 +0000

This is explained in more detail in the book "Human Being: reclaim 12 vital skills we’re losing to technology", which I think I found on HN a few months ago.

The first chapter goes into human navigation and it gives this exact suggestion, locking the North up, as a way to regain some of the lost navigational skills.

New comment by iib in "Ask HN: What Are You Working On? (December 2025)"

iib — Mon, 15 Dec 2025 08:58:15 +0000

Didn't see the website at first. Thank you!

New comment by iib in "Ask HN: What Are You Working On? (December 2025)"

iib — Sun, 14 Dec 2025 20:33:04 +0000

This seems really nice, and looks like something I have been wanting to exist for some time. I will definitely play with it when I have some time.

I know this is a personal project and you maybe didn't want to make it public, but I think the README.md would be better suited with a section about the actual product. I clicked on it wanting to learn more, but with no time to test it for now.

New comment by iib in "Ask HN: What Are You Working On? (December 2025)"

iib — Sun, 14 Dec 2025 20:23:00 +0000

That sounds awesome. But I have two curiosities: What are the problems of httpx? And was pycurl not enough for what you wanted to do?

New comment by iib in "Qwen3-VL can scan two-hour videos and pinpoint nearly every detail"

iib — Wed, 03 Dec 2025 14:52:57 +0000

I have been looking for the same thing, either from Meta's SAM 3[1] model, either from things like the OP.

There has been some research specifically in this area with what appears to be classic ML models [2], but it's unclear to me if it can generalize to dances it has not been trained on.

[1] https://ai.meta.com/blog/segment-anything-model-3/

[2] https://arxiv.org/html/2405.19727v1

New comment by iib in "Surprisingly, Emacs on Android is pretty good"

iib — Wed, 26 Nov 2025 05:51:12 +0000

For small edits, has anybody configured a leader-key scheme? Something like Doom Emacs has with space as a leader.

It seems to me to be the best possible configuration for Emacs on Android (on a phone) and I was wondering if I should invest time in such a solution.

strokes-mode.el would also be very nice, but apparently it doesn't have touchscreen support.

New comment by iib in "Gemini 3"

iib — Tue, 18 Nov 2025 21:33:12 +0000

As soon as I found out that this model launched, I tried giving it a problem that I have been trying to code in Lean4 (showing that quicksort preserves multiplicity). All the other frontier models I tried failed.

I used the pro version and it started out well (as they all did), but it couldn't prove it. The interesting part is that it typoed the name of a tactic, spelling it "abjel" instead of "abel", even though it correctly named the concept. I didn't expect the model to make this kind of error, because they all seems so good at programming lately, and none of the other models did, although they did some other naming errors.

I am sure I can get it to solve the problem with good context engineering, but it's interesting to see how they struggle with lesser represented programming languages by themselves.

New comment by iib in "The strangest letter of the alphabet: The rise and fall of yogh"

iib — Fri, 03 Oct 2025 06:15:54 +0000

Made me think of this SMBC comic[1], where there's a debate if being in English or Spanish, each with around a billion speakers, makes it rare or not.

[1] https://www.smbc-comics.com/comic/phonemes