aleksiy123

I guess it depends on what your definition of truly substantial is.

With the right objective function and enough compute I think you can definitely make progress. A lot of problems can be framed as search.

I think some of these proofs coming out is a good example of this.

GCP employees heart rate spiking at the title.

I don’t think that’s really true.

Both exist. I would say single player games tend to content in the range of 10+ hours. Think First Light, Ghost of Yotei in recent years.

Competitive and multiplayer games will tend more towards what you are thinking. CSGO, FIFA, and of course many others.

But I feel like even that doesn’t really capture the full range of everything.

Manual type? No cron job?

Practically Luddite

Is it just me or is this really not that crazy of an idea?

Polls are already a thing, and people love giving their opinion on things.

Combining social media and gambling while maybe not morally great. Seems like has potential to make a shitton of cash.

Betting is all over the place right now.

Wasn’t this case pretty much before?

The limits are 100 workers on free and 500 on paid.

And if need more then you can always go their platform which supports tenancy.

As long as you have a cronjob or similar to clean up the cost of having per PR preview is pretty much zero.

fighting the urge to rewrite everything and propagating the legacy code cycle.

Finally just bought a piece of my own hardware and got LLM to deploy k3s cluster on it.

I think diy homelab/hosting is more accessible than ever.

Cut costs on cloud spend and invest into AI spend.

For a solo dev on a budget, I think it just makes sense.

Not in the Clausewitz definitions I think.

Strategy would be the use software to achieve business goals.

Essentially why are we doing this at all.

If writing code is tactics and the end goal is strategy.

Is architecture operations?

Somewhere within c++ there is a subset of c++ that is a great language.

The problem of course is that no one agrees on which subset that is.

I pretty much always prefer using an options struct as soon as there is more than one optional argument.

Comes out cleaner because overriding a default argument doesn’t force you to also do all the positional arguments in front of it.

Designated initializers make it look really nice imo. I feel like the brackets are no big deal.

Python has sort of the opposite when you need to use *kwargs.

Interesting, I do think blending the fuzziness of models with the determinism of hard checks/conformance is the way too go.

But using some kind of metrics as guardrails/steering seems interesting.

Severance really captured that vibe.

It’s not even obvious that it isn’t conscious imho.

Or even have Claude actually go through the whole process of thinking about story structure, iterating on it, reviewing, editing, researching etc.

I feel like people expect Claude to just 1 shot a good story from their 2 sentence prompt.

But even a human needs to sit down and apply a structured or semi structured process over a non trivial amount of time/turns/iterations.

If you asked most people to write a short story out of nowhere with no context and 1hr. Most of them are gonna write some generic stuff.

Isn’t the fact that you just referenced it indicate that they do?

I feel like it’s probably just complexity.

Different workloads benefit from specific types of optimisations.

I think for big groups it’s not so much luck/randomness that is the key but complexity. Low complexity games are going to play better. They can be pure skill games. Many drinking games are (beer pong etc).

Luck/randomness is directly against determinism. A way of making feel less mechanical and opening up the combinatorial state space? Essentially increasing the fun/interest without introducing high complexity necessarily? As well as narrow the skill range as you say, but not necessarily over longer time horizons.

Like you can do a 2d matrix of luck and complexity.

Tic tac toe - low randomness, low complexity

Chess - low randomness, high complexity

Poker - med randomness, high complexity

Roulette - high randomness, low complexity

I saw someone in a different thread describe Google product/tool strategy as a: “monkey knife fight”

And tbh I can’t really argue with that.

how effective is RTK for you? worth using?

Its arguing that that source code that affects the behaviour of something should be easily discoverable from the point/points its behaviour affects. or alternatively more indirection/obfuscation is worse.

Its not so much about same file, as reducing distance to understanding, whether visually or by some sort of easily traceable path.

Like you would want to init a variable closer to its usage, Or that having a 100 wrapper functions is less understandable than inlining for a single statement, or global mutations are harder to trace then local, and that sometimes its easier to inline a single sql statement then split it out into a different file just because its 2 different languages.

Also, to be clear its possible to write CSS that exhibits less or more LoB. The file thing is more that I don't think HTML, CSS, JS "must" be written as separate files which is what the prevailing best practice used to be, justified as SoC. I just think splitting along the scope/behaviour lines rather than file type is more understandable.

End users and even other programs/extensions can load rules to alter your styles. I think thats about as opposite of locality of behaviour as it gets. (no judgment on customization on being good/bad).

With the rest I don't really strongly disagree. I think its just a question of complexity. For simple things its fine, but for complex apps with teams of people :shrug:

Or non binary. How much are these the same and how.

Use multiple trees.

that’s exactly the part that is anti locality of behaviour.

I don’t want/need cascade. I only care about components and building up from them. And I would rather have it be explicit over implicit and scoped/encapsulated.

Call it composition over cascade.

To be clear I think it’s possible to do this without tailwind. And tailwind has other out of the box features/opinions.

But it works well enough without too much friction.

Sorry maybe that wasn’t the best example. It’s not really about separation of files. But how they connect.

In sql your code may be in a seperate file but your app code is still clearly calling the sql. The inlining vs not inlining is just abstraction. You could use a function, or a separate file or not, a different language or not.

But there is a clear single call chain at the points where that behaviour is being applied and a single definition.

With css that’s not necessarily true. There’s a bunch of different rules that may or may not apply.

I think this assertion is where most of the conflict comes from.

There is a fair amount of people that disagree with the premise that it should be separated in that way (Including me).

I personally like this essay by the author of htmx on the topic

https://htmx.org/essays/locality-of-behaviour/

Also just better composition imo.

Practically I think this means components of scoped css, html, js.

People never seem to have the same complaint about mixing or separating app code and sql in the same way?

Tbh I have no idea, I’m mostly thinking about it from what I can do when using the frontier models, so I don’t think such low level changes are available to me.

But another dumb idea I had was a set of random words inspired by Terry Davis godsay https://github.com/orhun/godsays

With a more appropriate wordlist appropriate. Call it muses.

I’ve been thinking about how to get creativity out of llms, apart from temperature. The thing is even humans have a hard time with creativity.

Is it really surprising that llms don’t just one shot a unique story when they are all starting from roughly similar training data and state and a roughly 30 secs of processing time.

I had Gemini do some deep research for me around processes and frameworks to prompt ideation and creativity and they do exist. See SCAMPER and others.

Another interesting thing that comes up is using random decks of cards as prompts.

See Oblique Strategies, Deck of Lenses, the Story engine and similar.

I guess I still believe that even creativity is still fundamentally a type of search, as well as problem solving. Manipulating and or combining existing ideas in unexplored ways and breaking out of bias.

So I kinda want to experiment with these two approaches:

1. Longer running workflows that follow a framework and loop.

2. Some simple cli tools with these decks and a random draw to trigger interesting directions.

I think really just need to break llms out of their initial start state which is mostly the same for everyone.

And to run over longer horizons and so the higher level reasoning flows.

code monkeys