transdev12

I can’t really speak directly to your question because I don’t have LLMs write react, but I get great results from svelte.

At this point I don’t think it’s about training examples, once there is sufficient training data it becomes a problem of verifiability, ie how easily can the model check its work for success.

Because they’ve essentially exhausted pre training scaling and are looking to post training to expand capabilities, which is really just optimization via reinforcement learning against specific tasks aka bench maxing.

I generally use sonnet 5 for most coding tasks, a lot of coding is really pretty straightforward.

> the cost to build a modern agentic model is in the 10 figure range and growing

Source? The proliferation of labs building competent models would seem to suggest the opposite.

Strongly disagree with your premise.

Programming languages are what you build creative and interesting things from, building in safety into your tools is a good thing.

I wouldn’t want a nail gun that shoots in the wrong direction when you apply the incorrect amount of pressure. Software engineering over indexes on an obsession with the tools themselves over the things you make with them.

I’m trying to pitch my boss on something like bedrock/foundry/vertex where we can just swap the model and still have it serverless over an api.

Digital ocean particularly looks promising as well.

Claude comments look like this

//add returns the sum of x and y

//per section 2.1 of addition-implementation-plan.md sum is designed as the seam for user addition interfaces.

//previously sum added numbers, now it adds numbers

def add(x, y):

    return x + y

The corollary here is to have Claude write tests to enforce this. The only thing it is consistently responsive to is test failures.

You can stick to your morals without blowing things out of proportion.

“We are the only acceptable way to do things and no tradeoffs are acceptable” is fairly petty.

“We have a difference of opinion” isn’t.

I’ve been landing on go for a similar reason, which was the realization that LLMs are in many ways just massive cargo culting machines. People will call it “quality training data”, but really LLMs will just reflect the norms and behaviors of whatever ecosystem they’re using.

I like to think go’s lack of magic and standard library will lead to lower maintenance burden over time, but that’s mostly just vibes so far.

OpenAI really doesn’t have infinite money. They have a lot of money, sure, but it is being burned like crazy, we know this. It is widely known that they are deeply unprofitable.

Compare that with Apple, a company that throws off billions of cash every quarter. This isn’t a legit comparison.

I’ve been coming to hacker news for years (10+) and there has always been political commentary.

Real GDP is adjusted for inflation, nominal GDP is not.

Being in recession is typically defined as negative gdp growth.

So to answer your question, being in recession does account for inflation.