Hacker News: adamkochanowicz

New comment by adamkochanowicz in "GPT-5.2"

adamkochanowicz — Thu, 11 Dec 2025 22:02:17 +0000

I also love that I can leave the microphone on (not in live voice mode) while dictating to ChatGPT and pause and think as much as needed.

With Gemini, it will send as soon as I stop to think. No way to disable that.

This One Tool Will Help You with ADHD at Work

adamkochanowicz — Thu, 09 Oct 2025 17:11:43 +0000

Article URL: https://www.adamgrant.info/this-one-tool-will-help-you-with-adhd-at-work

Comments URL: https://news.ycombinator.com/item?id=45530432

Points: 1

# Comments: 0

New comment by adamkochanowicz in "Everything that's wrong with Google Search in one image"

adamkochanowicz — Wed, 24 Sep 2025 23:49:28 +0000

Kagi is worth every penny.

New comment by adamkochanowicz in "Ask HN: How do you fight YouTube addiction and procrastination? I'm struggling"

adamkochanowicz — Sun, 31 Aug 2025 18:42:18 +0000

If your addiction has gotten this far, it's time to start labeling it as just that, and there's no shame in it.

At a certain point you need to accept that you will not be able to willpower your way out of it. You need systems and strategies in place that cut you off from your addiction.

That can look like a lot of things that I'm not going to try to stuff into an HN comment but here's what works for me:

- Leaving the house with a dumb phone. I recommend using an old smartphone that is meticulously stripped away from bad things over purchasing a flip phone. You're eventually going to need to call up an uber, scan a QR code, and other such smartphoney things you need a dumb phone to do. Leaving your environment is also key. If you must, bring your actual phone with you, but fully powered off.

- Using a feature on your phone to cut yourself off from YouTube on a scheduled basis. Most phones have something like this by default, but there are also some third party apps that take it a step further.

- Have something you enjoy to take the place of YouTube. Entertainment is healthy to an extent. Taken too far, it becomes a distraction from cognitive processes you need to be regularly engaging in, to say the least.

A Research-Backed Cheat Sheet to Transitioning Mental States

adamkochanowicz — Wed, 27 Aug 2025 00:09:47 +0000

Article URL: https://www.adamgrant.info/research-backed-cheat-sheet-to-transitioning-mental-states#If%20your%20environment%20is%20intense,%20time-pressured,%20or%20noisy%20and%20it%20keeps%20pulling%20you%20into%20grind%20mode

Comments URL: https://news.ycombinator.com/item?id=45033901

Points: 1

# Comments: 0

New comment by adamkochanowicz in "Launch HN: April (YC S25) – Voice AI to manage your email and calendar"

adamkochanowicz — Mon, 25 Aug 2025 19:29:47 +0000

Huh? What relation does that have to do with setting email filters?

New comment by adamkochanowicz in "Launch HN: April (YC S25) – Voice AI to manage your email and calendar"

adamkochanowicz — Mon, 25 Aug 2025 19:28:51 +0000

I never set reminders. I just cancel right away. 99.9% of the time, it will just end when the trial is over, or if I just want to pay for a month, when that period is over.

New comment by adamkochanowicz in "Study mode"

adamkochanowicz — Tue, 29 Jul 2025 21:08:24 +0000

From what I can see, this just boils down to a system prompt to act like a study helper?

I would think you'd want to make something a little more bespoke to make it a fully-fledged feature, like interactive quizzes that keep score and review questions missed afterwards.

New comment by adamkochanowicz in "Show HN: Core – open source memory graph for LLMs – shareable, user owned"

adamkochanowicz — Tue, 01 Jul 2025 21:33:17 +0000

For those asking how this is different from a simple text based memory archive, I think that is answered here:

--- Unlike most memory systems—which act like basic sticky notes, only showing what’s true right now. C.O.R.E is built as a dynamic, living temporal knowledge graph:

Every fact is a first-class “Statement” with full history, not just a static edge between entities. Each statement includes what was said, who said it, when it happened, and why it matters. You get full transparency: you can always trace the source, see what changed, and explore why the system “believes” something. ---

New comment by adamkochanowicz in "Itter.sh – Micro-Blogging via Terminal"

adamkochanowicz — Fri, 09 May 2025 21:01:44 +0000

It looks completely garbled on my end

New comment by adamkochanowicz in "Get Out of My Head"

adamkochanowicz — Wed, 16 Apr 2025 13:02:54 +0000

It's akin to the days when people used google clones that used a black background to supposedly save on display energy use.

New comment by adamkochanowicz in "Get Out of My Head"

adamkochanowicz — Wed, 16 Apr 2025 13:01:43 +0000

They don't. Removing these tags will not result in any meaningful increase in page load time honestly. This is especially because most don't actually load up any linked file. Their weight is just the characters they are typed out in.

It's an informative webpage but it's not very effective optimization imo.

New comment by adamkochanowicz in "Skywork-OR1: new SOTA 32B thinking model with open weight"

adamkochanowicz — Sun, 13 Apr 2025 17:16:10 +0000

Also, am I reading that right? They trained it not only on another model, not only one that is already distilled on another model, but one that is much lower in parameters (7B)?