--- id: "/new/2026-w42/page/4/" title: "Index additions: 2026-W42 · page 4" creator: null creator_url: null creator_x: null url: "https://skillissue.dev/new/2026-w42/page/4/" level: null level_max: null category: null subcategory: null region: null license: null license_scope: null access: null models: null source_date: null date_added: null --- # Index additions: 2026-W42 Resources added to the index in this ISO week. This is a website archive, not a sent newsletter. [Beginner](/levels/beginner/index.md) [Intermediate](/levels/intermediate/index.md) [Advanced](/levels/advanced/index.md) [Expert](/levels/expert/index.md) 141 resources · page 4 of 5 ## Model Training - ### [Reinforcement Learning from Human Feedback (book)](/model-training/post-training-rl/nathan-lambert-reinforcement-learning-from-human-feedback/index.md) by [Nathan Lambert](https://rlhfbook.com/) A conceptual path through reward modeling and post-training methods. Advanced · West · closed resource · en - ### [Controlling Reasoning Effort in LLMs (Ahead of AI)](/model-training/post-training-rl/sebastian-raschka-ahead-of-ai/index.md) by [Sebastian Raschka](https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms) A free Ahead of AI article on training controllable reasoning effort. Advanced · West · closed resource · en - ### [Unsloth](/model-training/fine-tuning/unsloth-unsloth/index.md) by [Unsloth](https://github.com/unslothai/unsloth) Study local training and adaptation workflows for supported models. Advanced · West · open resource · en - ### [nanochat](/model-training/pretraining/andrej-karpathy-nanochat/index.md) by [Andrej Karpathy](https://github.com/karpathy/nanochat) [@karpathy](https://twitter.com/karpathy) A compact training harness spanning the model-development lifecycle. Expert · West · open resource · en - ### [DeepSeek-R1: Incentivizing Reasoning via RL (arXiv 2501.12948)](/model-training/post-training-rl/deepseek-deepseek-r1-incentivizing-reasoning-via-rl/index.md) by [DeepSeek](https://arxiv.org/abs/2501.12948) Study the reported reinforcement-learning recipe behind DeepSeek-R1. Expert · CN · closed resource · en - ### [The Smol Training Playbook](/model-training/pretraining/hugging-face-the-smol-training-playbook/index.md) by [Hugging Face (SmolLM team)](https://huggingfacetb-smol-training-playbook.hf.space/) A training account that includes failed experiments and engineering decisions. Expert · other · closed resource · en - ### [The Ultra-Scale Playbook](/model-training/training-infrastructure/hugging-face-the-ultra-scale-playbook/index.md) by [Hugging Face (nanotron)](https://nanotron-ultrascale-playbook.static.hf.space/index.html) Understand how parallelism changes memory use and training throughput. Expert · other · closed resource · en - ### [The FineWeb Datasets](/model-training/training-data/huggingface-fineweb/index.md) by [Guilherme Penedo and coauthors, Hugging Face](https://arxiv.org/abs/2406.17557) Study how filtering and deduplication affect pretraining data. Expert · other · open resource · en - ### [verl (HybridFlow)](/model-training/post-training-rl/verl-project-verl/index.md) by [verl project (originated at ByteDance Seed)](https://github.com/verl-project/verl) Explore how an RL training framework coordinates generation and optimization. Expert · CN · open resource · en ## Jailbreaking and red teaming - ### [Indirect prompt injection in the real world: how people manipulate neural networks](/security-and-red-teaming/prompt-injection/kaspersky-indirect-prompt-injection-field-study/index.md) by [Vladislav Tushkanov (Kaspersky)](https://securelist.com/indirect-prompt-injection-in-the-wild/113295/) Read a Russia-origin security team’s field study of indirect prompt injection and the implications for defensive risk assessment. Beginner · RU · closed resource · en - ### [NIST AI Risk Management Framework](/security-and-red-teaming/threat-frameworks-and-standards/nist-nist-ai-risk-management-framework/index.md) by [NIST](https://www.nist.gov/itl/ai-risk-management-framework) A government reference for organizing AI risk-management work. Intermediate · West · closed resource · en - ### [OWASP Top 10 for LLM Applications 2025](/security-and-red-teaming/threat-frameworks-and-standards/owasp-gen-ai-security-project-owasp-top-10-for-llm-applications-2025/index.md) by [OWASP Gen AI Security Project](https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/) Use a shared vocabulary for discussing risks in LLM applications. Intermediate · other · closed resource · en - ### [Simon Willison on prompt injection](/security-and-red-teaming/prompt-injection/simon-willison-simon-willison-on-prompt-injection/index.md) by [Simon Willison](https://simonwillison.net/tags/prompt-injection/) [@simonw](https://twitter.com/simonw) Follow an ongoing public record of prompt-injection research. Intermediate · West · closed resource · en - ### [The lethal trifecta for AI agents](/security-and-red-teaming/agent-and-tool-security/willison-lethal-trifecta/index.md) by [Simon Willison](https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/) [@simonw](https://twitter.com/simonw) A defensive framework for recognizing risky combinations of agent capabilities and untrusted inputs. Intermediate · West · closed resource · en - ### [Agentic misalignment](/security-and-red-teaming/safety-and-alignment-evals/anthropic-agentic-misalignment/index.md) by [Anthropic](https://www.anthropic.com/research/agentic-misalignment) A controlled study of risky behavior under conflicting agent incentives. Advanced · West · closed resource · en - ### [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](/security-and-red-teaming/jailbreak-research/chao-jailbreakbench/index.md) by [Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko and colleagues](https://arxiv.org/abs/2404.01318v5) Learn why jailbreak studies need consistent threat models, scoring and reproducible comparisons. Advanced · West · closed resource · en - ### [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](/security-and-red-teaming/prompt-injection/greshake-indirect-prompt-injection/index.md) by [Kai Greshake et al.](https://arxiv.org/abs/2302.12173) Foundational public research on indirect prompt injection. Linked only; no payloads reproduced. Advanced · West · closed resource · en - ### [Embrace The Red](/security-and-red-teaming/prompt-injection/johann-rehberger-embrace-the-red/index.md) by [Johann Rehberger](https://embracethered.com/blog/) Public case reports about security failures in deployed AI products. Advanced · West · closed resource · en - ### [LLAMATOR: authorized conversational AI security testing](/security-and-red-teaming/security-tooling/llamator-authorized-testing/index.md) by [Roman Neronov, Timur Nizamov and Nikita Ivanov / LLAMATOR](https://github.com/LLAMATOR-Core/llamator) A Russian-origin framework for assessing your own chatbots, with reviewable test histories and reports. Advanced · RU · closed resource · en - ### [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](/security-and-red-teaming/jailbreak-research/mazeika-harmbench/index.md) by [Mantas Mazeika, Long Phan and colleagues](https://arxiv.org/abs/2402.04249v2) Study a standardized approach to red-team evaluation and robust refusal without copying attack recipes. Advanced · West · open resource · en - ### [MITRE ATLAS](/security-and-red-teaming/threat-frameworks-and-standards/mitre-mitre-atlas/index.md) by [MITRE](https://atlas.mitre.org/) Connect AI threats with documented techniques, mitigations and cases. Advanced · West · closed resource · en - ### [garak - LLM vulnerability scanner](/security-and-red-teaming/security-tooling/nvidia-garak-llm-vulnerability-scanner/index.md) by [NVIDIA](https://github.com/NVIDIA/garak) A public scanner project for understanding classes of model failures. Advanced · West · open resource · en - ### [promptfoo](/security-and-red-teaming/security-tooling/promptfoo-promptfoo/index.md) by [promptfoo](https://github.com/promptfoo/promptfoo) Inspect a project combining application evaluation and security testing. Advanced · West · open resource · en - ### [Qwen3Guard Technical Report](/security-and-red-teaming/safety-and-alignment-evals/qwen3guard-technical-report/index.md) by [Haiquan Zhao and colleagues / Qwen Team](https://github.com/QwenLM/Qwen3Guard) Understand Qwen’s multilingual safety classifiers and the distinction between whole-response and streaming moderation. Advanced · CN · closed resource · en - ### [Design Patterns for Securing LLM Agents against Prompt Injections](/security-and-red-teaming/agent-and-tool-security/willison-prompt-injection-design-patterns/index.md) by [Simon Willison](https://simonwillison.net/2025/Jun/13/prompt-injection-design-patterns/) [@simonw](https://twitter.com/simonw) Summary of a paper's defensive agent architectures. Advanced · West · closed resource · en ## Frontier - ### [Responsible Scaling Policy](/frontier/policy-and-governance/anthropic-responsible-scaling/index.md) by [Anthropic](https://www.anthropic.com/responsible-scaling-policy) Read a lab’s published risk-governance commitments and revision history. Intermediate · West · closed resource · en - ### [Artificial Analysis](/frontier/model-releases/artificial-analysis-artificial-analysis/index.md) by [Artificial Analysis](https://artificialanalysis.ai/) Compare model and provider characteristics in one public analysis hub. Intermediate · West · closed resource · en - ### [Epoch AI - Data on the trajectory of AI](/frontier/trends-and-forecasts/epoch-ai-epoch-ai-data-on-the-trajectory-of-ai/index.md) by [Epoch AI](https://epoch.ai/data) Explore longitudinal datasets about models, compute and infrastructure. Intermediate · West · open resource · en - ### [Hugging Face Daily Papers](/frontier/research-feeds/hugging-face-hugging-face-daily-papers/index.md) by [Hugging Face](https://huggingface.co/papers) A community-curated route into newly discussed AI papers. Intermediate · other · closed resource · en - ### [Critiquing Anthropic’s Variant of Pacing the Frontier (ChinAI)](/frontier/policy-and-governance/jeffrey-ding-chinai-newsletter/index.md) by [Jeffrey Ding](https://chinai.substack.com/p/chinai-375-critiquing-anthropics) A free ChinAI essay examining arguments about international AI competition. Intermediate · CN · closed resource · en - ### [State of AI Report 2026](/frontier/annual-reports/nathan-benaich-air-street-capital-state-of-ai-report-2026/index.md) by [Nathan Benaich / Air Street Capital](https://www.stateof.ai/) A yearly synthesis of AI research, industry and policy developments. Intermediate · West · closed resource · en - ### [The current balance of power in open models (Interconnects)](/frontier/trends-and-forecasts/nathan-lambert-interconnects/index.md) by [Nathan Lambert](https://www.interconnects.ai/p/the-current-balance-of-power-in-open) A free Interconnects essay distinguishing open-weight and closed-model ecosystems. Intermediate · West · closed resource · en [Previous page](/new/2026-w42/page/3/index.md) [Next page](/new/2026-w42/page/5/index.md) [Plain-text Markdown copy](/new/2026-w42/page/4/index.md)