Hacker Newsnew | past | comments | ask | show | jobs | submit | haxel's commentslogin

Consider Tiny Tool Town? "A place for stupid-delightful tools made with love."

https://www.tinytooltown.com/


I also ride bike, and used to bonk, but it didn't take long for my body to adapt to using fat as fuel. Half the battle was mental: accepting that I truly didn't need to eat anything; my body already had all the fuel it needed.

Then I could wake up, ride hard for hours (hilly terrain), and feel no need to eat until the afternoon.


Agreed that it's mostly mental. Missing a meal isn't starvation, and the body/mind adapt.

I do IF and do most of my physical activity before my first meal every day. It was hard at first, but now it's when I have the most energy and clarity.


It's batteries-not-included, by design. Here's what it looks like with batteries (and note who owns this repo):

https://github.com/mitsuhiko/agent-stuff/tree/main

Perhaps benchmarks aren't the best judge.


AI studio also has a bug that continuously counts the tokens, typing or not, with 100% CPU usage.

Sometimes I wonder who is drawing more power, my laptop or the TPU cluster on the other side.


The creator is very aware. Its original name was "shitty coding agent".

https://shittycodingagent.ai/


then do SCA and backronym it into something acceptable! That's even better lore :)


There's a fair chunk of irony here in that Mario is being both anti-memetic with his naming choices and contrarian in his design decisions, and yet he still finds himself dunked in the muck of popularity as the backbone of OpenClaw.


You mean Software Component Architecture? Do you want to bring down the wrath of IBM!


Good call, he'll have to name it Shitty COdingagent, or "SCO". No one will sue over that name.


ding is a good name for an agent


I use Mistral (7B v0.2 instruct, 6-bit quantized) to generate the title-text for messages that I send to myself via a Discord bot.

Right now, I'm prompting Mistral to generate these titles in "clickbait" style. I fold the topic of the message and other context into the prompt.

My intention is to shift my attention to the message, which shifts my attention to something else I need to do, because I tend to over-focus on whatever I'm doing at the moment.

It doesn't matter whether what I'm doing at the moment is "good" or "bad". Based on probability, I should almost always switch my attention when I receive such a message because I should have switched an hour ago.

To guarantee consistent JSON output, I use a llama.cpp grammar (converted from JSON schema)

Generation is via CPU (Ryzen 5800) because it's an async background operation and also because my 1070 GPU is being used by Stable Diffusion XL Turbo to generate the image that goes along with the message.


If you send yourself messages via a Discord bot, you lose the privacy advantage of running a LLM locally.

Discord does not have end-to-end encryption for messages.


Indeed. Currently, my primary concerns are a) surprise b) accessibility c) efficiency and d) self-containment.

Surprise, because that draws my attention better. Not interested in guardrails here.

Accessibility, because I can involve my sons without friction.

Efficiency, because using Discord lets me skip building or finding a component (for now).

And I still get a degree of self-containment because Discord is the only piece I'll need to swap out. Bonus that it doesn't have a recurring cost until then.

Yet privacy still matters to me. Despite being Discord-compromised, the detailed personal context within the prompts remains private. The data that determines the timing and topic of each message remains private as well.


SEEKING WORK - Mostly remote

Location: West coast Canada. Remote: Yes (occasional Vancouver onsites OK).

Frontend: SolidJS, React, Material UI, and more.

Backend: FastAPI, Flask, and more (mostly Python)

Services: PostgreSQL, OpenZFS, GlusterFS, Redis, Docker Swarm, Kubernetes, and more.

Additional: Article writing, report writing, diagramming, research, conceptual communication, and more.

I have decades of experience at all levels of the tech stack, from provisioning hardware up through services, backends, frontends, and including architecture, app design, and UIs from scratch.

When necessary, I will synthesize and implement a novel solution (while making the most of existing components).

I've been brought in multiple times as an emergency fixer and executed the rescues successfully.

I've also taken on high-level roles requiring decision-making, planning, and communication skills to go along with demonstrated high integrity.

Willing to take a crack at anything substantial.

Email: clyde6@gmail.com


Not OP, but I swapped over to Regolith a couple of months ago on my laptop and now it's on my main workstation too. Coming from Ubunutu MATE on both. Very happy with it.

It's my first time using i3 or any tiling WM for that matter. Took about a day to get used to the basics (sane defaults), and that's mostly all I've needed so far.

My one attempt to use the dedicated installer didn't work properly so instead I installed Ubuntu and then Regolith from PPA.


Sane defaults is key. I've seen lots of comments about how nice i3 is, but also about how it's a rabbit hole of small config changes until you reach some nice settings.

I like to adapt myself to default settings instead of the other way around, because that allows me to seamlessly move between workstations. So a carefully selected choice of default settings is a very nice thing to have.


Developer statement

IMPORTANT: Android + Chrome only! (for now)

They say you can't manage what you don't measure.

This is a system to help people who feel fine but are worried about becoming infected by COVID-19 or any other dangerous virus. If this is you, now you can actively measure your risk and see a live dashboard in your Android phone's notification bar.

Your regularly refreshed dashboard shows your own risk pattern and compares it with your recent past as well as the risk patterns of other people. This makes it easier for you to manage both your behavior patterns and your mental health.

It's an early release by a single developer, extended from an existing platform. Please don't expect perfection.

Geographical awareness is an obvious next step. Infection/symptom awareness is another.

Feedback welcome!


I'm building a way to roughly (and simply) track your own viral risk in real-time and compare it with others.

https://howfunctional.com/viral-risk

Android-only right now. Precision is not the intention. Getting the ball rolling is.

The tracker is currently in prototype form so it may look or act a bit odd, not least because I quickly extended an existing platform.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: