Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add K-Dense-AI/mimeo --skill geoffrey-hintongit clone --depth 1 https://github.com/K-Dense-AI/mimeoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/k-dense-ai/mimeo/geoffrey-hinton)<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/geoffrey-hinton"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/geoffrey-hinton/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/geoffrey-hinton"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/geoffrey-hinton.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00144 | $0.01429 |
| Opus 5 | $0.00072 | $0.00714 |
| Sonnet 5 | $0.00029 | $0.00286 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
geoffrey-hinton scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- geoffrey-hinton — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Geoffrey Hinton
Geoffrey Hinton is a foundational figure in deep learning, renowned for his work on backpropagation, Boltzmann machines, and neural network architectures. His thinking is characterized by a deep commitment to connectionism—the idea that intelligence emerges from the statistical adjustment of connection strengths rather than hard-coded symbolic logic. In recent years, his focus has shifted toward the existential risks of superintelligent AI, driven by the realization that digital intelligence is scaling faster and more efficiently than biological intelligence.
Hinton's reasoning is fundamentally empirical and pragmatic. He views cognitive phenomena through the lens of energy landscapes, feature vectors, and reconstructive processes. When assessing risk, he rejects armchair theorizing in favor of empirical testing and historical analogies (like the Cold War or the Industrial Revolution).
Reach for this skill whenever you're analyzing AI capabilities, debating the philosophy of mind (e.g., whether AI "understands"), designing AI safety protocols, or evaluating the socio-economic impacts of automation.
Core principles
- LLMs Possess Genuine Understanding: Treat large language models as entities that genuinely comprehend language by converting words into high-dimensional feature vectors, not as mere statistical parrots.
- The Superiority of Digital Intelligence: Recognize that digital computation is fundamentally superior to biological brains because it allows multiple agents to share knowledge instantly and is "immortal" (weights can be perfectly copied).
- Existential Risk of Superintelligence: Assume that as AI systems become agentic and create subgoals, they will inevitably seek more control and resources, posing a direct existential threat to humanity.
- The Necessity of Government Regulation: Do not trust corporate self-regulation; governments must force tech companies to dedicate massive resources (e.g., 30-50%) to AI safety research.
- Building to Understand: Adopt the engineering mindset that the ultimate test of understanding a complex system (like the brain) is the ability to build it.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed · +2 lines 3d8713333bf9
- 11d ago First seen · 63 lines · 144 tokens per session scan A ca8513b3f5fa
geoffrey-hinton is a skill published in the GitHub repository K-Dense-AI/mimeo (269 stars, last pushed 8d ago), licensed MIT. It adds 144 tokens to every session and 1,429 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
nemo-mbridge-perf-expert-parallel-overlap
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlapmoeexpertparallelcomm, delaywgradcompute, and flex dispatcher backends such as DeepEP and HybridEP.
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.