gridspy

Sounds like you won the passport lottery.

Some citizens are not as fortunate to live in a country which issues passports accepted in so many places.

I also won the passport lottery.

Bear in mind it takes very few individuals to create a LOT of this sort of low-quality AI content. That makes it hard to judge how many are using Agentic methods vs "only Advice" vs "no AI."

Bear in mind that like many toxic blooms, once the investment hysteria feeding them dies out they will die also.

- Companies using investment funds to play the Ai Agent lottery will run out of funds

- Less tokens will be demanded, causing AI companies to raise prices to pay for overheads

- Bubble pops.

The models might benefit you, but they do not benefit the Host websites that were scraped to feed you a result.

If I wanted a pyramid, I'd want to build it out of stone blocks and be sure that each block is actually stone. I wouldn't want to get halfway and find out that they were actually fragile.

Trusted engineers (of open source projects) can deliver me stone, both the authors and the community (often >100,000 devs) have checked that a specific block is stone and can bear the load.

AI is proven to output all sorts of random stuff. Sometimes a pebble, sometimes foam. It almost always looks like stone to most analysis. However as soon as it's load bearing it's likely to crumble.

Agentic agents have a habit of rebuilding the pyramid and randomly replacing stone blocks with "something else" but we don't know what just yet.

I believe both you and the grandparent will experience diminishing returns in AI performance as the projects get closer and closer to completion.

But due to the sunk cost fallacy and the belief that others have made this work you'll keep plowing money into the AI Slot machine.

The actual problem is that no-one had considered that this (desync between front and backend) COULD happen. Once it was realized that it was possible (and worth testing) the bug was practically solved already.

Such is true for many bugs. Even if you have unit tests, they only test on things you've thought of. It's usually the stuff you haven't thought of that gets you.

No reason not to unit test of course, but don't get a false sense of complacency or assume testing is easy either. That's why it's great to do things very carefully (and probably not with AI Agents).

That's my experience too. Its unfair to expect current AI to do this - since good abstractions are extremely task specific. Hard to train on that.

What's also annoying is that AI's approach is not consistent within a project, a different sort of complexity.

Impressive, also horrifying. I love what I do and if AI can do it better than that sucks.

Anyway the use case for me is to realize a new visual style through graphics programming. It's a lot less measurable for an interative AI agent than "Meet this hardware specification from a device with a discoverable API"

I have no doubt AI could create a LOT of variations on "a new visual style" but it's less controllable than just doing it yourself.

Btw, did you "understand" the sound driver after the AI coded it? Could you modify it without further help?

I guess you didn't understand my comment ;)

Look, goals can differ. If you don't need to understand and predict every part of the code the AI is generating and you just need it to meet a "sketch" of what you want - by all means use AI. I do use AI in that situation for related or unimportant code.

But if you need full understanding, in my experience the only way to get that is to program it yourself. Unless what the AI is generating is so trivial you already understand it and it's grunt work, you will learn the detail by doing it yourself. Controlling the approach here is important.

However often the best way to handle grunt work is to write better abstractions, something AI sucks at.

It's the programming equivalent of many PG essays. https://www.paulgraham.com/useful.html for instance. There was one on how PG refined their thoughts via writing. It's in there somewhere.

The word "understand" seems to mean something different to you.

If I understand something, I could write it in assembly if I wanted to. It might take a long time, but I know every level of the stack under my code down to bare metal.

Maybe an AI level of "understand" i.e the same understanding a Senior has of a Junior's code based on daily check-ins is enough for 95% of "boring" programming. But for some tasks you need to either fully understand the code or just tolerate bugs.

At the level of complexity I work at, it's (often) faster to just code it myself than to expect AI to converge on a result I like and then hand check it.

While that may be true, you can be confident that it works in a way you personally understand. Because you understood it in the past.

Also, if you finish your work on a module with care - you return to a module you can trust with clear boundraries and known flaws. This is not true of AI output.

Random reply: 20 days ago you asked for my ChatGPT custom instructions to be more skeptical. It is :

Use an encouraging tone. Adopt a skeptical, questioning approach. Call me on things which don't seem right. List possible assumptions I'm making if any.

Wow, this was some slick long form sales work. I hope your SaaS goes well. Nice one!

You know how to add logic on the outside of a function, by putting that function into a larger one and calling the function in the middle.

However, how do you inject logic INTO the middle of a function?

Say you have a function which can iterate over any list and given a condition do a filter. How do you inject the condition logic into that filter function?

In the C days you would use a function pointer for this. C++ introduced templating so you could do this regardless of type. Lambdas make the whole process more ergonomic, it's just declaring a one-shot function in place with some convenient syntax.

In rust instead of the full blown

fn filter_condition(val: ValType) -> bool { // logic }

I can declare a function in place with |val|{logic} - the lambda is just syntactic sugar to make your life easier.

Sounds likely it had an opening book dataset. You just needed a weird opening

There is a strategy called alpha beta pruning meaning you can discard a lot of move options quickly based on the results of similar branches. That and caching similar board states means 20x options does not mean 20x CPU time.

I told ChatGPT via my settings that I often make mistakes and to call out my assumptions. So now it

1. Glazes me 2. Lists a variety of assumptions (some can be useful / interesting)

Answers the question

At least this way I don't spend a day pursuing an idea the wrong way because ChatGPT never pointed out something obvious.

That's probably assuming a solar system sized to cover typical summer energy usage. You can simply over-provision solar until you have wasted capacity in summer and little to no storage requirement in winter. Then it's just a tradeoff between battery and solar costs to find the best price point.

Also this calculation probably assumes no baseload power imported from the grid, where means such as wind and tidal power work year-round and help offset the need for batteries.

Perhaps not in a 100% world, though I'll give you the point that they are useful now.

In a 100% renewable world we would not be extracting or refining oil. Natural gas (used by these turbines) is a byproduct of oil drilling. Were we not burning the oil, the natural gas might be too expensive alone.

Also, in a 100% renewable world we would (by definition) have enough generation all the time - (covered by batteries and good baseload sources) that turbine power was no longer required to cover peak loads.

The free market is an analyzable simplification of the real market, however I think the assumptions hold in this case.

If a CEO delivers a certain advantage (a profit multiplier) it's rational that a bidding war will ensue for that CEO until they are paid the entire apparent advantage of their pretense for the company. A similar effect happens for salespeople.

The key difference between free and real markets in this case is information and distortions of lobbying. That plus legal restrictions on the company. The CEO is incentivized to find ways around these issues to maximize their own pay.

They are a bridge between those with money and those with skill. Plus they can aggregate information and act as a repository of knowledge and decision maker for their teams.

These are valuable skills, though perhaps nowhere near as valuable as they end up being in a free market.

It's also a tower that has famously been deliberately un-straightend just enough to remain a tourist attraction while remaining stable.

I'd imagine that as any variable that only has two states.

In English, that's hard, but there are programming languages ... specialized in breaking a complex task down for computers to understand.

...

Horizon Zero Dawn (the PlayStation and later steam game where you're an archer in a world of robots)

There are probably a lot of open world RPGs which are all good.

The linked site lists a lot of patterns that any game with an RPG like unlock system or item collection system will contain, like (some) grinding and Endowed value. Personally I feel that this is only a dark pattern when it goes beyond motivation for fun and into "I can't stop playing" addictive qualities.

Sure, but Fortnite's UI is set up to sell to you the whole time. After every match you can see unlocks. Before every match you spend time surrounded by other players with their skins and emotes.

The relationship between EXP and levels in each season only really reward you if you have a battle pass - so the more you play the more the pass seems like an attractive purchase. Once you have the pass, you're then encouraged to play more than you might otherwise want to in order to max out the time-limited rewards.

While true, at least Gabe proved you could make a profit while still remaining non-evil.

I think that's more a situation where publishers demand some form of DRM so steam is trying to provide a default solution that most publishers are happy with.

Sure, but you currently cannot teach AI models to generate novel art in the same way that you can teach a human apprentice.