--- title: "Failed-ML vs LLMs-from-scratch" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/kennethleungty-failed-ml-vs-rasbt-llms-from-scratch" tools: ["kennethleungty-failed-ml", "rasbt-llms-from-scratch"] --- # Failed-ML vs LLMs-from-scratch *GraphCanon updated Jul 11, 2026* ## Verdict Pick Failed-ML when license: Failed-ML is MIT, LLMs-from-scratch is Other; pick LLMs-from-scratch when license: LLMs-from-scratch is Other, Failed-ML is MIT. [Failed-ML](https://towardsdatascience.com/when-ai-goes-astray-high-profile-machine-learning-mishaps-in-the-real-world-26bd58692195) reports 753 GitHub stars, 51 forks, and 0 open issues, last pushed Jun 14, 2024. [LLMs-from-scratch](https://amzn.to/4fqvn0D) has 99k stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. Figures are from public GitHub metadata via [Failed-ML's repository](https://github.com/kennethleungty/Failed-ML) and [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch). | | [Failed-ML](/tools/kennethleungty-failed-ml.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Tagline | Compilation of high-profile real-world examples of failed machine learning projects | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | | Stars | 753 | 98,899 | | Forks | 51 | 15,183 | | Open issues | 0 | 4 | | Language | - | Jupyter Notebook | | Adopt for | - | LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. | | Persona | - | - | | Runtime | - | - | | License | MIT | Other | | Categories | Computer Vision, LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Failed-ML](/tools/kennethleungty-failed-ml.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Steady (60%) | | Days since push | 757d | 38d | | Open issues (now) | 0 | 4 | | Full report | [trust report](/tools/kennethleungty-failed-ml/trust.md) | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | ## Decision facts: LLMs-from-scratch - **Adopt for:** LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. ## Choose when ### Choose Failed-ML if… - License: Failed-ML is MIT, LLMs-from-scratch is Other. - Tags unique to Failed-ML: classification, computer-vision, data-engineering, data-quality. - Also covers Computer Vision. ### Choose LLMs-from-scratch if… - License: LLMs-from-scratch is Other, Failed-ML is MIT. - Tags unique to LLMs-from-scratch: attention mechanism, finetuning, from-scratch, generative-ai. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ## When NOT to use Failed-ML - Last GitHub push was 758 days ago (dormant maintenance, Jun 14, 2024). Validate activity before betting a new project on Failed-ML. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## When NOT to use LLMs-from-scratch - - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 - a deeper learning experience. ## Common questions ### What is the difference between Failed-ML and LLMs-from-scratch? Failed-ML: Compilation of high-profile real-world examples of failed machine learning projects. LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. See the comparison table for live GitHub stats and shared categories. ### When should I choose Failed-ML over LLMs-from-scratch? Choose Failed-ML over LLMs-from-scratch when License: Failed-ML is MIT, LLMs-from-scratch is Other; Tags unique to Failed-ML: classification, computer-vision, data-engineering, data-quality; Also covers Computer Vision. ### When should I choose LLMs-from-scratch over Failed-ML? Choose LLMs-from-scratch over Failed-ML when License: LLMs-from-scratch is Other, Failed-ML is MIT; Tags unique to LLMs-from-scratch: attention mechanism, finetuning, from-scratch, generative-ai; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I avoid Failed-ML? Last GitHub push was 758 days ago (dormant maintenance, Jun 14, 2024). Validate activity before betting a new project on Failed-ML. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### When should I avoid LLMs-from-scratch? - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience. ### Is Failed-ML or LLMs-from-scratch more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 753). Stars measure visibility, not whether either tool fits your constraints. ### Are Failed-ML and LLMs-from-scratch open source? Yes - both are open-source projects on GitHub (Failed-ML: MIT, LLMs-from-scratch: Other). ### Where can I find alternatives to Failed-ML or LLMs-from-scratch? GraphCanon lists graph-backed alternatives at [Failed-ML alternatives](/tools/kennethleungty-failed-ml/alternatives) and [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) ([Failed-ML markdown twin](/tools/kennethleungty-failed-ml/alternatives.md), [LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/kennethleungty-failed-ml-vs-rasbt-llms-from-scratch.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Failed-ML or LLMs-from-scratch? Failed-ML: Dormant. LLMs-from-scratch: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for Failed-ML and LLMs-from-scratch? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Failed-ML trust report](/tools/kennethleungty-failed-ml/trust); [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=kennethleungty-failed-ml`](/api/graphcanon/graph?tool=kennethleungty-failed-ml) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_