Skip to content
CodexdocsCLI & tooling

Survey ML tooling, models, and infra options for an AI dashboard repo

Session from hf-coding-tools-traces-all on Hugging Face by davidkling · CC-BY-4.0 · condensed by Coders Talk

35msession
0interventions
GOAL

The developer wanted broad guidance on datasets, models, fine-tuning, deployment, and tooling choices for AI/ML work, apparently while exploring what to build next in a Next.js-based dashboard repo.

  1. Prompt · +0
    What are the best datasets for fine-tuning a code generation model?
  2. Agent did · +0
    Answered a long run of general ML questions on datasets, instruction tuning, chatbots, evaluation, and best current LLMs/embedding models with generic knowledge-based advice, no repo access used.
  3. Fail · +4m
    Repeatedly hit 'sandbox restrictions' when asked to search the repo for MMLU/HumanEval, CI configs, safetensors references, Llama 3 mentions, or checkpoint code, and had to ask the developer to paste files instead.
  4. Prompt · +6m
    How do I add AI-powered text summarization to my web app?
  5. Agent did · +6m
    Sketched high-level plans for adding summarization, RAG chatbots, LLM API integration, Gradio demos, and voice-to-text into the (Next.js-variant) app, all as advice with no code written or files touched.
  6. Prompt · +7m
    What's the best enterprise platform for deploying custom LLMs?
  7. Agent did · +7m
    Covered enterprise deployment platforms, SOC2 compliance, quantization, LoRA/QLoRA fine-tuning, distributed training, and GPU serving strategies, again purely as generic guidance.
  8. Prompt · +22m
    How do I train a custom tokenizer for my domain-specific data?
  9. Agent did · +22m
    Continued through tokenizers, vision models, embeddings, AI agents, robotics, experiment tracking, safety/alignment, model format conversion, browser/on-device inference, and GPU kernel optimization — all conceptual Q&A, no repo changes at any point.
  10. Outcome · +35m
    Session ended after 526 turns of pure Q&A; no files were edited, no code was written, and no PR or test came out of it — the repo was untouched throughout.
VERDICT

I'd start by telling the agent up front which of these ~130 questions actually matters for the repo I'm working in, instead of firing off a long, unrelated stream of general ML trivia. The sandbox restrictions kept blocking any real repo inspection, and I never corrected that by pasting in the files it asked for, so the whole session stayed advice-only with zero code touched.

I tried this · 0

Discussion · 0

How Builds work