smrtinsert

It's the railroading that's being decreased. Various tech orgs are pushing back on everyone in the company pushing PRs as they realized is profoundly wasteful and unfair for people to push 10 PRs and then just dump it into someone elses lap to validate. "Claude already made a PR for it" doesn't hold up when you can't make a meaningful judgement on the output. Not every org is there yet, but my read is its happening at places like Goldman.

Everyone has gotten a boost in effectiveness because they're using the same multiplier. No one really cared before how bad some developers were because they were likely cheap, onshore or offshore.

The label might come later, but cooperative or adverserial behavioral patterns matter deeply when deploying agents to act as weapons of defense or business builders.

Who made this jquery spaghetti? If you couldn't properly organize stateless functions, you were doing something wrong.

Anecdotally, sveltekit 2 was super quick to use for me. I tried building a somewhat interactive app with htmx and found the user experience was often incorrect on the Claude 4 family models. I switched to sveltekit 2 and it produced what wanted almost immediately. Features were added instantly. Even today with React and Opus 5.5 it couldn't match the development performance of version 2.

That said, both are "fast enough" and if you're on an enterprise plan, the cost difference is neglible. I waste way more more tokens due to poor or imprecise requirements than I do on development.

I mean, how fast do you need it to be? If you're running lambdas with cold starts all day long yes, java is a problem. Otherwise, occasional restarts of java services are quick assuming they're probably stateless. A few seconds? Whats the problem that needs to be solved here?

Where are the competitor to the big frontier labs? The Chinese providers are demonstrating everything can be done cheaper and practically identical. I'm surprised upstarts aren't showing up.

Don't you put yourself at the mercy of bot banning with this approach? It's probably good for poc use cases, but I wouldn't count on it in production.

And that is precisely all it is, a demo. Reminder that BYDs are held at bay in an anti free market policy specifically because American car companies cannot compete with its low cost and quality. We're wasting time and money on this type of tech.

This engineering in this demo was only designed o get lucrative government contracts.

Let's skip the exceptionalism and go straight to the numbers next time.

sounds like a market opportunity

Is it possible to quantize the model? Don't think I want to run 8 gigs on my local just for decisions but curious about it for sure

When you frame it as if we're in the Pets.com era of AI the continued gold rush makes sense.

I can't take it seriously at all. Whats the community sell? Make AI slop games? Were game developers wondering "gee, how can I make even LESS money". Not all possible marketplaces or services have to exist.

How many times would you let an actual human hallucinate or be incorrect before you fired them?

Sounds like exactly the daily I deal with when agents try to create product requirements from multiple sources, except to a much much worse extent.

But people aren't communicating freely. They are being throttled, shadow banned, refused etc. In some cases these are political candidates. Since this is one of the main channels of consumption these obvious and well documented manipulations are having a massive impact on political outcomes.

Doubt. High level plans have less detail to worry about.

Fintech, easy to trigger some sort of failure mode or obvious gap once specs get detailed enough and the prompt intents become specific enough. Doesn't require exhausting available context. Opus 5 did feel like a regression, will hold out judgement on 5.5 which seems much more promising.

Looking forward to being hacked DNAwise by rogue OpenAI agents

What else are you supposed when keeping up with platforms proves too difficult!

More Java strawman arguments. How do we live with BuilderFactoryFactoryBuilders! Every day we cry ourselves to sleep!

Somehow still theoretically valued at 3 trillion. I just don't see a path forward for Ameican frontier providers when competitors can give absolutely massive savings elsewhere. It's like losing manufacturing all over again.

People dont even trust meta with their personal data anymore but somehow they'll use it to run every aspect of their lives? This feels like another big failure in the making. Give me an AI that doesn't use my data at all and maybe I'll use it. I already have Google AI Mode for that. Does that steal my data too, maybe, but at least it doesn't have Metas history of abusing repeatedly. They burned that bridge so many times even non techies know not to trust Meta.

this leap is like jumping over to jupiter from earth

I'm come to realize that movies and literature have nearly 0 ability to warn the people about what can could come to pass and why it is bad.

Said it before, I'm almost sure the awful text it generates is part of the fingerprinting feature.

I still winced

640k ought be enough for this AI. I'm not sure takes like these are helpful. It's widely acknowledged that this is a technological shift, like electricity, like industrialization, etc. It could be (good or bad) but most likely (good AND bad). Does anyone really believe, sincerely, that AI will be the great equalizer? It's a hilarious proposition. They are working their hardest to make sure that its not imo.

Is there something like that but simply a GUI web wrapper around subscriptions and memory layer? I want a web ui. I don't think in terms of these personality types though, my tasks are dynamic. For example, claude can run N agents in one window right now and be accurate about it, so I scope agent by project level.