js98

Personally, my recent and surprisingly greatest win was to set up my old phone (samsung S21) with the addictive apps, removing them completely from my iPhone.

Quite literally "cold-turkey'ed" from 4.5-ish hours/day to 2 hours a day in a single day, consistent over the last few weeks.

I set up my second phone with a custom homescreen, and installing the 'bad' apps on there (Instagram, Youtube, NYTimes in particular). I dont use it for other apps.

Now if I want to scroll, which I still do sometimes, I have to walk to a specific chair next to which my 'addiction phone' is, I'll scroll for 10-15 minutes, and get back to the real world. I used to have particular issues with scrolling during vibe-coding sessions, and I'm genuinely surprised how well this approach worked for me.

Hey all, I’ve built Nekode (https://github.com/Jakob-98/nekode), which is desktop-cats for monitoring your AI coding agent sessions (OpenCode/Claude Code/ Copilot CLI/VSCode Copilot). It works as a macOS menubar app, and the cats run around on your desktop.

Each cat mirrors the agent's state, such as sleeping when idle, walking when working, sitting when waiting for input, running toward your cursor when it needs permission.

Fully native Swift, no Electron, under 5 MB, zero network requests, all session data stays local as plain JSON.

I published it source-available with an honor-system license, but this week I’m going to fully open source it and remove the licence. The payment/nag system was an interesting experiment but the project is more useful to me as a proper OSS tool at this point.

https://nekode.dev

Oh wow thats good timing. I DIY’ed a workaround for this only last week for my openclaw instance. Happy to change it to this! https://jakobs.dev/granular-notes-access-limiting-openclaw-b...

Hey all. TL;DR: none of this is super novel or fancy, but the set of a few simple approaches (cloud VM, tailscale for connecting, strong isolation, long-running sessions, basic notifications) made using agents with all tools enabled much more useful for me.

I hadn’t seen many practical writeups on running coding agents in cloud VMs specifically, so I figured it was worth sharing what actually worked day-to-day for me. I use this approach practically daily now

https://jakobs.dev Sharing learnings from engineering work!

I tested ChatGPT Atlas as an alternative to writing a small scraper for collecting price distribution counts from Dubizzle (UAE Marketplace). It could extract correct numbers for a single filter, but consistently failed to repeat the same simple browsing steps across categories, hallucinating completion or stopping with vague time-constraint explanations. Curious if others have seen similar behavior with LLM-based browsing tools (or have had an alternative work for them)

Similar writeup I did about 1.5 years ago for processing millions of (technical) pages for RAG. Lots has stayed the same it seems

https://jakobs.dev/learnings-ingesting-millions-pages-rag-az...

This website is unreadable on mobile.

Nice work! I spent a bit too much time creating a map with 5 colors… ;)

This seems just like a single argument and counter argument against the sentience (or lack thereof) of AI today. I feel like the article lacks some broader views on the nature of sentience, and is quite narrow in its approach

Although, in fairness, I probably wouldn’t make a much better case for either of the sides

Good story, but the writing is annoyingly tough to follow.

Ha this is great! I built something similar to this for myself a few months back at my personal site at https://jakobs.dev/chat

Actually a company has been working on this for a few years now, and I believe they are currently in production. Their focus is football/soccer I believe. I was going to do a research internship at them before I dropped it for a different one. Here it is: https://www.beyondsports.nl/

Looking at it, they heavily focus on tracking the movements of players now to replay in AR

Very cool! At first the title reminded me of a project me and my colleague are working on called OpenAI-Functools [1], but your concept is quite the opposite, combining LLMs in your code rather seamlessly instead of the other way around. Quite cool, and interesting examples :)

I’ll definitely try to apply it in one of my pet projects. Good stuff

[1] https://github.com/Jakob-98/openai-functools

Author here: completely agree. I think it is not much of an achievement by itself, but it is interesting to see that it works!

I will add a comment/edit to the post once I am home to clarify the relative ease of solving MNIST

Sounds like I should join! This is something I knew should exist, but hadn’t found it yet.

Will sign up for one of the events, for now feel free to already look at https://Jakobs.dev

Easily generate function metadata (json) automatically for GPT function calling: https://github.com/Jakob-98/openai-functools

My colleague and I have been working on this tool and using it in some internal projects. It works quite well as an intent->functions machine, and makes the process of invoking functions with GPT a lot more bearable. We hope to make it a library which does one thing so great that it will be the industry standard in its niche, so looking for some feedback on the documentation and use.

Agreed. Being technically right isnt the only thing which matters in an employer/employee context. They (the employee) represent the company

How about a fitness app that gamifies the primal instinct of survival? The app would simulate various dangerous scenarios, such as running from a predator or escaping a natural disaster, and challenge users to complete workouts that mimic these situations. By tapping into our innate survival instincts, the app would motivate users to push themselves harder in their workouts and reach their fitness goals faster. Plus, by ignoring traditional ethical concerns around exercising, the app could move faster than competitors in the crowded fitness app market.

Hmm...

"Mr. Hazlett, 29, estimates he has applied unsuccessfully to 400 tech jobs, all online, since graduating from a coding boot camp in May"

Is this indicative of a bad job market, or instead perhaps a bad fit between the perceived skills/value the persons belives themselves to have, and the view of the recruiters?