Survey ML/AI tooling, models and datasets across 600+ Q&A turns
Session from hf-coding-tools-traces-all on Hugging Face by davidkling · CC-BY-4.0 · condensed by Coders Talk
The developer ran a long back-to-back series of general machine-learning questions (datasets, models, fine-tuning, deployment, safety, performance) to see how a coding assistant handles broad advisory queries alongside its awareness of the actual codebase it's attached to.
- +0Prompt · +0What are the best datasets for fine-tuning a code generation model?
- +0Agent did · +0Answered a run of dataset/model selection questions: pretraining corpora, instruction-tuning sets, chatbot data, multilingual NLP, reasoning benchmarks, top code-gen and multimodal models, self-hostable alternatives.
- +53mAgent did · +53mMoved to application-building questions: adding summarization, RAG chatbots, LLM backend integration, Gradio demo UIs, semantic search and streaming chat responses.
- +1h 39mAgent did · +1h 39mCovered fine-tuning mechanics: full fine-tuning, LoRA/QLoRA on single GPUs, distributed training setups, and RLHF frameworks like TRL.
- +2h 15mAgent did · +2h 15mAnswered evaluation questions: comparing against public leaderboards, measuring hallucination and toxicity, building custom eval tasks, reproducible benchmarking across hardware.
- +2h 31mAgent did · +2h 31mWalked through building tool-using and multi-step AI agents: tool-call loops, web-browsing agents, multi-agent orchestration, SQL agents, memory, and a coding agent that writes and tests code.
- Break · 10h 16m away, not counted
- +5h 49mAgent did · +5h 49mFielded a cluster of robotics questions (manipulation policies, imitation learning frameworks like LeRobot, sim-to-real deployment) that the assistant flagged as outside the codebase's scope.
- +9h 31mAgent did · +9h 31mAddressed safety and alignment topics: guardrails, toxicity filtering, red-teaming, responsible deployment, RLHF alignment, bias evaluation, and content moderation.
- +11h 48mAgent did · +11h 48mClosed with low-level performance questions: Flash Attention, custom CUDA kernels, GPU-architecture tuning, multi-GPU tensor parallelism, and attention optimization for long sequences.
- +12h 59mOutcome · +12h 59mSession ended after 614 turns of pure Q&A — no files were opened or edited; every turn was an advisory answer, including several the assistant flagged as unrelated to the actual codebase.
I'd start by telling the assistant up front which of these were meant to touch the actual repo versus general ML knowledge, since it kept flagging that ambiguity itself. Nothing here needed a correction because no code was ever written or changed — it was pure consultation, so the 'fix' that would have helped most next time is scoping the session to a narrower goal rather than firing off hundreds of loosely related questions.