Viewing profile — payneio

And by "wisdom of the croud", I'm referring to sharing what works well and what doesn't and building good approaches into the frameworks... encoding human expertise. We do it all t…

Compiling and evaluating output are types of fact checking. We've done more extensive automated evaluations of "groundedness" by extra ting factual statements and seeing whether or…

I feel that. I've been on an emotional roller-coaster for three years now. I didn't expect any of this before then. :O

Ah! Gotcha. Thanks for the clarification. The use cases I'm thinking that require cloud architecture are scaling up with GPUs (for self-hosted intelligence workloads). Also, Wild C…

Also... "scammer and AI grifter"?? Damn dude. It's any early-stage open-source experiment result and, mostly, just talking about how it makes me question whether or not I'll be pro…

I get it. I've been through cycles of this over the past three years, too. Used a lot of various tools, had a lot of disappointment, wasted a lot of time and money. But this is the…

Thanks for the extract. I feel quite comfortable that my post is on-topic and gratifying. I understand others may disagree (and do in nearly every post on HN)

So, what we do is automate the hand-holding. In your physics simulation example, you can have the system attempt to compile on every change and fix any errors it finds (we use stri…

How are you verifying your claims? I'm actually seeing results that you describe as being impossible.

Not just you. A lot of people think that, I'm sure. Not sure what you mean about the organizational abstractions. FWIW, I've worked in five startups (sold one), two innovation labs…

It's not, actually. It's a glimpse into a research project being built openly and made freely, by the engineers building it, to anyone who wants to take a look. The products will c…

Yes. These are all the same points I used to believe until recently... in fact the article I write two months earlier was all about LLMs not being able to think like us. I still ha…

Yes. Please read it. I'm looking for collaborators. The links in this article point to recent work on Wild Cloud so you can see where it's currently at. Wild Cloud will is a networ…

What's wrong with "self promotion"? The point of this space has always been promoting projects. That's what Y Combinator is all about

Yes, I code a lot. My GitHub is public as are many of the projects I work on.

FWIW, finished an eval of claude code against various tasks that amplifier works well on: The agent demonstrated strong architectural and organizational capabilities but suffered f…

Here's a writeup of the project for more context: https://paradox921.medium.com/amplifier-notes-from-an-experi...

I've tried it. It works better than raw Claude. We're working on benchmarks now. But... it's a moving target as amplifier (an experimental project) is evolving rapidly.

Hey all! I'm one of a handful of developers on this project. Great to see it's getting some interest! For context, we are right in the middle of building this thing... multiple reb…

Thanks for pushing for a realignment of product expectations. I agree.

I wrote up some details of investigations of a chatbot we created in Microsoft Research using a technique of creating synthetic memories with LLMs and RAG. Key takeaway is that it …

Too true.