smrtinsert

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