Unlike similar apps such as Focus Friend or Forest, which use active timers to police screen time, my app is an inversion that works like an idle game; All screen time is tracked all day, (with double the punishments at night), and upon check-in, you get feedback on your device usage.

https://automatisolutions.com/products/phreepet/

- As the context window grows the LLM will become less intelligent [1] - Once your conversation takes a bad turn, you have effectively “poisoned” the context window, and are asking an algorithm to predict the likely continuation of text that is itself incorrect [2]. (It emulating the “belligerent side of OSS maintenance” is probably quite true!)

If you detect or suspect misunderstanding from an LLM, it is almost always best to remove the inaccuracies and try again. (You could, for example, ask your question again in a new chat, but include your terminal output + clarifications to get ahead of the misunderstanding, similar to how you might ask a fresh Stack Overflow question).

(It’s also a lot less fun to argue with an LLM, because there’s no audience like there is in the comments section with which to validate your rhetorical superiority!)

1 - https://news.ycombinator.com/item?id=44564248 2 - https://news.ycombinator.com/item?id=43991256

(I'd also argue that "understanding" and "functional brain" are unfalsifiable comparisons. What exactly distinguishes a functional brain from a turing machine? Chess once required a functional brain to play, but has now been surpassed by computation. Saying "jobs that require a human brain" is tautological without any further distinction).

Of course, LLMs are definitely missing plenty of brain skills like working in continuous time, with persistent state, with agency, in physical space, etc. But to say that an LLM "never will" is either semantic, (you might call it something other than an LLM when next generation capabilities are integrated), tautological (once it can do a human job, it's no longer a job that requires a human), or anthropocentric hubris.

That said, who knows what the time scale looks like for realizing such improvements – (decades, centuries, millennia).

I'm my mind, writing the prompt that generates the code is somewhat analogous to writing the code that generates the assembly. (Albeit, more stochastically, the way psychology research might be analogous to biochemistry research).

Different experts are still required at different layers of abstraction, though. I don't find it depressing when people show preference for working at different levels of complexity / tooling, nor excitement about the emergence of new tools that can enable your creativity to build, automate, and research. I think scorn in any direction is vapid.

Remote: Yes, or Hybrid/In Person

Willing to relocate: No

Technologies: My current favorite stack for building products is with TypeScript, React, (or React Native), PostgreSQL, Vite, Linux (Arch, Debian, or Ubuntu), Bash, and Nginx

Résumé/CV: https://drive.google.com/file/d/1fjHlGavAHEn1CK2-mDI-FPkuLIS...

Email: jdesmond@automatisolutions.com

LinkedIn: https://www.linkedin.com/in/joshdesmond/

Hello! I'm a fullstack app developer. I can build a product or own features from start to finish. I would love to join your team or help out, whether as a contractor or full time hire!

https://lichess.org/learn

``` When making edits to the script, ensure the script remains

- Idempotent - Functional after a fresh install of a virtual machine

Additionally, keep things stupid simple and avoid:

- Unnecessary error checks - Defining colors and custom logging functions - Bells and wistles - Backups - Branching Paths - Script Arguments ```

I find it helps cull back the LLM 's overenthusiasm for abstractions.

LLM assisted programming, however? – instant flow state. Instead of thinking in code I can think in product, and I can go straight from a pencil sketch to describing it as a set of constraints, and then say, "make sure it's ARIA compliant and responsive", and 95% of the work is done.

I feel similarly about configuration heavy files like Nginx or something. I really don't care to spend my time reading documentation, I'd rather copy paste the entire docs into the context window and then describe what I want in English.

Also good for SQL. And library code for a one off tool or API. And Bash scripting.

I also think that language matters - An Emacs function is much more esoteric than say, JavaScript, Python, or Java. If I ever find myself looking for help with something that's not in the standard library, I like provide extra context, such as examples from the documentation.

If you ask an LLM to "Write me a poem", expect the equivalent of what others are calling analogous to hotel art: generic and inoffensive. However, if you inject your personalized soul and suffering into the context window, there's no reason not to expect the transformation of that soul into indistinguishably human-like prose.

I won't share the full content, because it was personalized to me and my moment.

I am quite curious though, how art without an author will grow into society.

That Edgar Allan Poe is seminal in both genres makes me appreciate an already amazing character that much more! I would 10/10 recommend anyone watch season one of the series.

This thread now has me tempted to finally get into reading Poe himself, (among Lovecraft and the Altered Carbon books for more Poe influenced writing).

The biggest part of my strategy is to do a lot of stutter steps/dash dancing to try and collect the power up as close to the ghost as possible. Doing so is more likely to lead to a sort of "combo" state where your pacman can spawn kill the ghosts without any additional input. Fast reflexes can keep your combo state going if you know when to stutter step and when to turn back around and start comboing again in the opposite direction Getting your game state into such a combo state is even stronger in the late game as your pacman moves so fast it can almost always set up for a lot of safe kills quickly. And additionally, as you pointed out, by getting a ghost kill for every power up you get, you hasten the speed at which you grow your multiplier

I've found that substantial efforts to get off of platforms that distract me can work, but it's very difficult and should very much be thought of as a hybrid problem of both your personal self, and your technological environment around you. If you're surrounded by distractions, you will find yourself distracted; however, if you simply crave distraction, blocking things will only lead to you getting distracted by the next best source of entertainment.