Results for “autotuning”

Automatically collects dialectic memory to fine-tune local models.

Fine-tune a TAO model with standard supervised training, evaluation, and export, with AutoML bypass and platform-specific credential intake.

Run automated hyperparameter optimization for NVIDIA TAO models using AutoMLRunner, supporting multiple search algorithms and experiment tracking.

Diagnose and optimize slow-loading, high-memory, or low-FPS USD scenes using a structured workflow with profiling, validation, and mutation phases.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Automates repetitive infrastructure and deployment tasks with Terraform, OpenTofu, Ansible, GitHub Actions, and n8n, enforcing safe practices like plan review and confirmation before applying changes.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

当设定个人或工作目标，希望目标本身能带来持续的内在动力和满足感时

Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill, benchmark skill, eval my skill, run evals on. Outputs: an improved SKILL.md, a results log, and a changelog of every mutation tried.

Pre-commit/ship code review: Codex default; optional Claude, Pi, Droid, Copilot, Cursor, or OpenCode.

Visual Instruction Tuning

When reviewing code, generate the complete corrected version — not just the issues, but the exact fixed code ready to copy-paste.

Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)

[OMX] Strict autonomous loop: $deep-interview -> $ralplan -> $ultragoal (+ $team if needed) -> $code-review -> $ultraqa

Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants the assistant to improve how it operates, asks for a reflection, or wants a durable fix instead of a one-off apology.

Visual Prompt Tuning

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when asked to "auto review", "autoplan", "run all reviews", "review this plan automatically", or "make the decisions for me". Proactively suggest when the user has a plan file and wants to run the full review gauntlet without answering 15-30 intermediate questions. (gstack) Voice triggers (speech-to-text aliases): "auto plan", "automatic review".

Give your agent a budget, a target, and a deadline — it does the rest. Orchestrates DSL + Opportunity Scanner + Emerging Movers into a full autonomous trading loop on Hyperliquid. Race condition prevention, conviction collapse cuts, cross-margin buffer math, speed filter. 3 risk profiles: conservative, moderate, aggressive. Use when setting up autonomous trading, creating a trading strategy, or running a scan-evaluate-trade-protect loop.

Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Runs a structured code review as a pre-commit or pre-ship gate, supporting multiple review engines and scope governance.

AutoAugment: Learning Augmentation Strategies from Data

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Every autoscaling decision is driven by one of three trigger types, and mature

Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics. Use when the user runs /si:review or asks what has been learned and what should be promoted or pruned.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Audits and rewrites user-facing copy across web and mobile codebases, improving clarity, tone, and actionability of labels, errors, CTAs, and empty states.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Plan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.