arxiv:2410.07520
🔄 In a Training Loop
Tarun Jain
lucifertrj
AI & ML interests
Deep Learning, FPGA, and ML
Recent Activity
posted an update about 1 month ago
Two ideas from Andrej Karpathy’s tips on making LLM output easier to digest went into my last video:
> I put ASD-STE100 in the script guidelines so the narration sounds less AI-written
> then turned my project into a launch video with the Brag skill in Claude Code. (with voice)
+ ASD-STE100 also works well for video scripts.
🔗 Watch on how to build these launch videos with single prompt: https://www.youtube.com/watch?v=OBX3b71n5EE liked a model about 1 month ago
google/embeddinggemma-2 repliedto their post about 2 months ago
You can now automate EDD (eval-driven development) with Coding Harness Agents
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPkOrganizations
