LeafItAlone

> I miss discussions and debates about architecture and solutions to problems.

If you aren’t having these, then your team is using these tools wrong. AI assisted coding should open you up to more of precisely these conversations. Then use them to implement that.

> only to be passed the modern equivalent of a LMGTFY link hurts in a very particular way

Apt analogy, because if you are asking questions that can be answered with the AI equivalent of a Google search, you are wasting someone else’s time.

> Plumbing pays pretty well

Plumbing does not pay well for the average plumber. Not doctor-well at least, which is what you are responding to.

Can some plumbers make good money? Absolutely. But you need to do dirty, body-breaking work for years.

There’s nothing wrong with being a plumber and it’s a profession we surely need young people to go into. But the pay and trade offs vs a white color job will lean heavily in direction of the latter.

LLMs can provide the intentions of the code they write. To say they can’t is saying that they can’t fix bugs, which they very obviously can do effectively. So, just tell them to write the intention in the way you want it. If you are implicitly providing the direction in the prompt, make that explicit - you then it will have the context for the change while working and for the commit message and you’ll likely get a higher quality output.

Fix your harness. Provide rules, format, and good examples.

You probably had those for the humans in your team for when new hurts join, right? Just direct your LLMs to them and you’ll have a much better experience.

Just like you can’t expect a new junior dev to know what to do without direction, the same applies with LLMs.

A big win of LLMs in my book is the absolute reduction of commit messages with just “fixes” or “updates”. Commit messages have become more meaningful and useful, even if far from perfect.

We have one dev who uses LLMs to write the code, but still commits by hand. Most of his messages are of the type above, and none of them are useful.

This is certainly a problem with out-of-the-box usage. But easily overcome. Spend time updating your harness. This is not a hard problem to solve and there are many helpful guides out there.

We basically took our documented (human) SDLC process and applied it to the relevant harness hooks. Since our SDLC docs talked about what good comments looked like and what to avoid, we basically had the direction for the tools. Opus 5 did throw us a loop and increase the verbosity and decrease usefulness of the text, but refining our documentation cleared that hurdle within about a day.

You need a better harness. LLMs are significantly better at this than humans. Add it as a step in your LLM process and your documentation will always be up to date.

I personally find it unbelievable that you have access to all of the public GitHub projects available and still think the typical developer writes good code.

We’ve been tracking performance and bugs for years. Including commits those bugs were introduced in. So when LLM-generated code started working its way into our codebases, we have the before and after. And even comparing human generated code today with LLM-generated code today.

Depends on the prior state.

For one codebase I work in, LLM written code is noticeably and measurably (we have literally measured it for bugs, performance, etc.) better than what existed before. So the LLM code is a welcome change.

Dude, just be nice and let people have fun. Raspberry Pi’s have made it possible for people to do things they never otherwise would have done! It is pretty amazing!

That seems a little unfair.

1. It’s so much easier using RPis for that work. It can be done with no soldering at all and there are tons of easy to use libraries. Not having to solder is a huge plus IMO and I have a workstation with iron, hot plate, air gun, etc. ready and waiting.

2. Why hate on doing it Python? Even ESP32 embedded development ecosystem treats Python well with CircuitPython and MicroPython.

3. At least they are making something!

4. Even a simple ESP32 is overkill for what you described, so why are you hating on people using an RPi when your suggestion is just as laughable when taking your hardcore embedded stance?

As someone who has been working on embedded work since RadioShack was a good source of components - let’s not gatekeep makers.

That page is… a lot, on mobile.

Here’s the tech specs page, which is also busy: https://pollen-robotics.com/microduck/press-kit/

Interesting how all of the replies so far to your comment assume we’d just release the existing animals into the wild instead of just not breeding more.

This is such an ironic blog post it hurts.

What is snarky about that?

The answer is so that they can charge different prices per credit. If you buy low amounts, they can charge one price. If you buy in bulk, they can offer a discount. The usage is the same, but they can differentiate price per usage to give people more a favorable price if they are better customers.

Is there anything wrong with that?

I would love to hear more about this!

Don’t worry. This advice has been going around for much more than 2 months, including links posted here as well as official advice from the major companies (OpenAI and Anthropic) themselves. The tools literally have had plan mode as a first class feature.

So you probably wouldn’t have any clout anyways, like all of the other blog posts.

>what's the value of paying someone for a product like this vs just building it myself?

Same thing it’s always been. Convenience. Including maintenance costs. AI tools have lowered the bar significantly on some things, so SaaS offerings will need to be better, but I don’t want to reinvent every wheel. I want to build the thing I want to build, not the things to build that.

Just like I go to restaurants instead of making every meal myself.

I lived in such a place and never had power outages. Mostly because the power company came through on a regular basis (two years or so) and chopped down and trees that could cause problems. Some areas definitely looked terrible from a beauty standpoint, but it meant keeping power.

Who paid the $20k?

I’ve had a cheap (was $15) single salad spinner, for about 15 years. Decent amount of usage in that time, but not professional level.

So my question to you is: what the heck are you doing to your salad spinners?

All of this was on a Bambu A1 Mini?

These are the types of things I want to print. My Ender 3 was so finicky, I only got a few out before I gave up.

>simply moving to greener pastures, whether that be NC, TN, NV, or FL

Yeah, but then they’d be in NC, TN, NV, or FL which, frankly, sounds absolutely miserable. They made the right choice by being in NYC.

Adafruit seems to be doing very well where they are. Why would they want to suffer in such junk states like those with worthless governments when they could continue to be where they are and are happy? They’d also be scraping the bottom of the barrel in those places for talent for the necessary in-person positions. The stars up mentioned sure are cheaper, and they still cost more than they are worth.

I’ve tried most of the coffee making tools and fads, including the above mentioned recipe. I’ve spent thousands and hours and hours of time chasing the feeling others like you describe.

It was so easy for me to go back to a cheap drip coffee maker and pre-ground coffee. I realized that I’ll never appreciate the flavors and process as much as the investment would call for.

I wish I could read like you then because it’s distracting to me, and clearly many others, when people write like that.

I really wish your comment also had some capitalization and punctuation so it was easier to parse. Even ChatGPT had different interpretations.

But PT (sorry, I guess it’s stylized, pt) has written like this for years, long before the recent LLM-based AI revolution (maybe given his position in the tech community he had much earlier insight into what the machines want). It has been one of the reasons his messages always seem aggressive, IMO.

This is not acceptable behavior on this forum.

None of it is reasonable. This is an online version of a schoolyard tiff. Neither side in that email chain is reasonable or mature.