Viewing profile — megadragon9

[dead]

I did something similar. It started off as a "self-improving agent" project, inspired by autoresearch, then later on I reframed it as "harness training" (discrete program search) b…

[dead]

The core idea is to keep the LLM frozen and train everything around it (e.g. prompts, context management, tools, repair loop). The harness is one editable Python file. In each epoc…

I worked on this project ( https://github.com/workofart/harness-training ) for the past few months to reframe "Agent-driven Self-improving Harness" to "Harness Training". The idea …

Interesting project. Do you think manual memory management help understand computational graph lifecycle better, or does it distract from backprop itself? btw, I went down the micr…

Model built and trained using a hand-built deep learning library (numpy primitives)

I'm continuing to expand my own deep learning library [1] built with numpy-primitives to support LLM post-training techniques like supervised fine-tuning (SFT) and reinforcement le…

looks like elon web services (EWS) is the master plan all along :D

I don't think the market will swallow the stock offerings until we see early signs of GDP growth attributable to these entities. But until then, I think the cost is higher than the…

I recently wanted to see whether an AI agent could self-improve a harness to solve terminal bench tasks. It’s possible for an AI agent to propose a meaningful one-time change to th…

I'm continuing to expand my own deep learning library [1] (PyTorch-clone built with Python and Numpy) to support LLM post-training techniques like supervised fine-tuning (SFT) [2] …

Interesting to see more demand shaping mechanisms applied to LLM inference. Even though the "batch processing" feature is already available. I guess this "promotion" is to test the…

Thanks for sharing! It's inspiring to see more people "reinventing for insight" in the age of AI. This reminds me of my similar previous project a year ago when I built an entire P…

Love the educational value of this "nano-sized" project. This reminded me of the from-scratch project I created to learn about deep learning libraries, neural networks all the way …

Reminds me of this HN discussion (Writing Code Was Never the Bottleneck): https://news.ycombinator.com/item?id=44429789