Viewing profile — DenisM

I wish they don’t stop. Make it easier to skip past.

Double-harnessing distortions seems like a weak point. I wonder if it’s just a temporary measure and long term it’s about writing custom harness going straight to inference APIs ac…

+1 well written, well paced article. Pleasure to read. Have you tried measuring Gemini? now that you have the router it should be a simple task. Thanks!

How can Smart Router achieve higher task completion rate compared to any of the base models if all it does is dynamically switch base models based on cost??

Years ago I learned that GM’s financial arm made more money than the car company. The other day I also read that airlines make more money from selling points than from flying peopl…

This might grow bigger than cobol. There will be a large number of companies that will be staffed entirely by vibe coders and when an issue crops up that cannot be debugged by them…

I kinda dislike where your comment leads, but I can’t argue with the logic either. Time for self-reflection I suppose. Maybe a better way of doing this is to ask the experts to do …

Diabolical. I’m not sure if I’m frightened or fascinated… , I’m thinking of where can this lead if applied iteratively. Like, slop supernova followed by by a slop brown dwarf?

Suggestions? My attempts to get the agent to summarize the discussion largely failed. Other options I’m considering is capturing design, implementation plans, and maybe sub-plans. …

So what is tre answer then? I feel like “discretion” parties missing. Do we need some kind of special discretion model?

Not quite a Bear Sterns scale event.

How do you know what you built is good? That was the pivot for me - I defined it for myself as it’s something that makes a positive contribution to my users.

For clarity: Indian government.

Remarkably, it took non-AI workloads 25 years to grow from zero to 3%, and it took AI only ~ 2.5 years to get to 2%. This puts a number to my intuitive feeling that things move an …

Where did the tokens go?

> So what about the other 3%? That's not "massive"? Or it gets a pass because it's not AI? How did you read that in my comment?

Select quote: * 5% of electricity in the United States is used to power data centers. For AI-focused ones specifically, it’s probably around 2%.* I think it’s massive.

This media frenzy can go on forever tho. A Bear Sterns moment would be more solid. Oracle might ge the first to collapse if things go south, so we might be fine until then(?).

In my little ai bubble the original blog post was very influential. It does sound immodest, but could also be true.

Register two domains in different jurisdictions, with neither serving its own jurisdiction, and a redirect for stray users.

Not clear where 2x claim in the headline came from, I don’t see it in the linked site.

> the runaway inference truck. Nicely done, thank you.

No sarcasm. In that thread we discussed recursive, interleaved application of code and prompt. No morphing, however. Thanks for dynamic workflow pointer. I don’t know if I like Jav…

The idea of morphing prompts to code and back is revolutionary. You may want to read earlier discussions https://news.ycombinator.com/item?id=48881112 And https://news.ycombinator.…

> I tested the language against cold agents I was procrastinating on that, thanks! > the recursive nature It’s not clear from you answer if we’re on the same page. Your options are…