Viewing profile — zuzuen_1

"We make a tentative calibration of the self-sustaining ac celeration condition using the existing data that is available, measuring AI capabilities using the Epoch Capabilities In…

I think we need better classification and taxonomy on erroneous LLM behaviors than the catch-all term "hallucinate"..

Tbh, I think troubleshooting / investigation is really a lot different from feature development. Wrong fixes upstream are really bad because software downstream starts relying on t…

Wait, this is insane! And the method they use to classify an outage seems solid as well. Imagine being a Github dev working in this environment.

I've been building Modulo AI for the past year - an AI system that fixes GitHub issues. Early versions took 5+ minutes to analyze a single issue. After months of optimization, we'r…

One pain point such a PL could address is encoding tribal knowledge about optimal prompting strategies for various LLMs, which changes with each new model release.

Perhaps when LLMs introduce a lot more primitives for modifying behvavior such a programming language would be necessary. As such for anyone working with LLMs, they know most of th…

I would be more interested in Qodo's performance on the swe-bench-multilingual benchmark. Swe-bench-verified only includes bugs related to python breakages. The best submission is …

Does anyone have a benchmark on the effectiveness of using embeddings for mapping bug reports to code files as opposed to extensive grepping as Qodo, Cursor and a number of tools I…