Digital Garden

Clippings

Showing 1 of 1 entries
NameReadPublishedAuthorDescriptionSource
Understanding and Coding the KV Cache in LLMs from Scratch2025-06-17Sebastian RaschkaI'm an LLM Research Engineer with over a decade of experience in artificial intelligence. My work bridges academia and industry, with roles including senior staff at an AI company and a statistics professor. My expertise lies in LLM research and the development of high-performance AI systems, with a deep focus on practical, code-driven implementations.Open
Showing 26 of 26 entries
NameReadPublishedAuthorDescriptionSource
Inside the Go Playground - The Go Programming Language2013-12-11Andrew Gerrand 12 December 2013How the Go playground works.Open
Defer, Panic, and Recover - The Go Programming Language2010-08-03Andrew Gerrand 4 August 2010An introduction to the Go's defer, panic, and recover control flow mechanisms.Open
Go Slices usage and internals - The Go Programming Language2011-01-04Andrew Gerrand 5 January 2011How to use Go slices, and how they work.Open
Building Effective AI Agents—AnthropicDiscover how Anthropic approaches the development of reliable AI agents. Learn about our research on agent capabilities, safety considerations, and technical framework for building trustworthy AI.Open
How we built our multi-agent research system2025-06-13AnthropicOn the the engineering challenges and lessons learned from building Claude's Research systemOpen
The Open Source LLM Agent Handbook How to Automate Complex Tasks with LangGraph and CrewAI2025-06-03Balajee Asish Brahmandam, FreeCodeCampEver feel like your AI tools are a bit...well, passive? Like they just sit there, waiting for your next command? Imagine if they could take initiative, break down big problems, and even work together to get things done. That's exactly what LLM agents...Open
The Agentic AI Handbook A Beginner's Guide to Autonomous Intelligent Agents2025-05-28Balajee Asish Brahmandam, FreeCodeCampYou may have heard about “Agentic AI” systems and wondered what they’re all about. Well, in basic terms, the idea behind Agentic AI is that it can see its surroundings, set and pursue goals, plan and reason through many processes, and learn from expe...Open
Don’t Build Multi-Agents2025-06-18CognitionFrameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.Open
Multi-Persona Prompting2025-04-08Dan Cleary, PromptHubSee how a new prompting method can generate better results than standard and Chain of Thought (CoT) methodsOpen
Meta Prompting2025-03-27Dan Cleary, PromptHubCheck out our deep dive on the latest meta prompting methods, like DSPy and TEXTGRAD, and the best prompt generator tools out there.Open
10 Best Practices for Prompt Engineering2025-03-05Dan Cleary, PromptHub10 easy-to-implement tips to get more out of your prompts, with any model. Get better responses and reduce hallucinations.Open
How's Linear so fast? A technical breakdown2026-05-02Dennis Brotzkybreakdown of the architecture behind Linear's speed: local-first sync, MobX observables, instant first loads, and a keyboard-first design.Open
How to Design My First AI Agent2025-06-03Fabiana Clemente, Towards Data ScienceThe foundations of designing an AI agentOpen
Rewriting Bun in Rust2026-07-08Jarred SumnerWhy & how we rewrote Bun from Zig to RustOpen
A Guide to Quantization in LLMs2024-02-21Kartik Talamadupula, Symbl AIThe capabilities of Large Language Models (LLMs) have grown in leaps and bounds in recent years, making them more user-friendly and applicable in a growing number of use cases. However, as LLMs have increased in intelligence and complexity, the number of parameters, or weights and activations, i.e., its capacity to learn from and process data, […]Open
Deploying Large Language Models — Tips & Tricks2023-09-27Manoranjan RajguruHosting a large language model (LLM) can be a complex and challenging task. One of the main challenges is the large model size, which requires significant computational resources and storage…Open
LLM distillation demystified a complete guide2024-02-13Matthew Casey, Snorkel AILLM distillation isolates task-specific LLM performance and mirrors it in a smaller format—creating faster and cheaper performance.Open
The Coding Assistant Breakdown More Tokens Please—Max Kan, SemiAnalysisHands On With GPT 5.5, Opus 4.7, DeepSeek V4, Why Benchmarks Are Bad, and Who’s Going To WinOpen
LLM Distillation and Pruning Maximizing Efficiency2024-10-25Sapien IOLearn all about LLM distillation and pruning strategies. Understand how these techniques optimize large language models for improved efficiency and performance.Open
Understanding and Coding the KV Cache in LLMs from Scratch2025-06-17Sebastian RaschkaI'm an LLM Research Engineer with over a decade of experience in artificial intelligence. My work bridges academia and industry, with roles including senior staff at an AI company and a statistics professor. My expertise lies in LLM research and the development of high-performance AI systems, with a deep focus on practical, code-driven implementations.Open
The Big LLM Architecture Comparison2025-07-19Sebastian Raschka, PhDFrom DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture DesignOpen
What are the differences between BPE and byte-level BPE2024-02-04Stack OverflowIn Roberta, I'm not sure if the model use BPE or byte-level BPE tokenization, are these techniques different or the same ? Can someone explain ? ThanksOpen
Is IF expensive2008-11-24Stack OverflowI can't, for the life of me, remember what exactly our teacher said that day and I'm hoping you would probably know.The module is "Data Structures and Algorithms" and he told us something along theOpen
Life of an inference request (vLLM V1) How LLMs are served efficiently at scale2025-06-27UbiCloudvLLM is an open-source inference engine that serves large language models. We deploy vLLM across GPUs and load open weight models like Llama 4 into it. vLLM sits at the intersection of AI and systems programming, so we thought that diving into its details might interest our readers.Open
Chunking Strategies10moVictoria SlocumFrom context engineering to embeddings, chunking might be the most underrated part of the pipeline. It has more of an impact on performanceOpen
5 Essential LLM Quantization Techniques Explained2025-04-18—Learn 5 key LLM quantization techniques to reduce model size and improve inference speed without significant accuracy loss. Includes technical details and code snippets for engineers.Open
Showing 26 of 26 entries
TitleAuthorSourcePublishedCreatedModifiedDescriptionTagsPublishReadPath
PromptHub Blog: 10 Best Practices for Prompt Engineering with Any ModelDan Cleary, PromptHubhttps://www.prompthub.us/blog/10-best-practices-for-prompt-engineering-with-any-model2025-03-052025-06-112025-06-1110 easy-to-implement tips to get more out of your prompts, with any model. Get better responses and reduce hallucinations.clippingsSoftware/Clippings/10 Best Practices for Prompt Engineering.md
5 Essential LLM Quantization Techniques Explained—https://apxml.com/posts/llm-quantization-techniques-explained2025-04-182025-07-032025-07-03Learn 5 key LLM quantization techniques to reduce model size and improve inference speed without significant accuracy loss. Includes technical details and code snippets for engineers.clippingsSoftware/Clippings/5 Essential LLM Quantization Techniques Explained.md
A Guide to Quantization in LLMsKartik Talamadupula, Symbl AIhttps://symbl.ai/developers/blog/a-guide-to-quantization-in-llms/2024-02-212025-07-022025-07-02The capabilities of Large Language Models (LLMs) have grown in leaps and bounds in recent years, making them more user-friendly and applicable in a growing number of use cases. However, as LLMs have increased in intelligence and complexity, the number of parameters, or weights and activations, i.e., its capacity to learn from and process data, […]clippingsSoftware/Clippings/A Guide to Quantization in LLMs.md
Building Effective AI AgentsAnthropichttps://www.anthropic.com/engineering/building-effective-agents—2025-06-182025-06-18Discover how Anthropic approaches the development of reliable AI agents. Learn about our research on agent capabilities, safety considerations, and technical framework for building trustworthy AI.clippingsSoftware/Clippings/Building Effective AI Agents.md
Post by Victoria Slocum on LinkedInVictoria Slocumhttps://www.linkedin.com/posts/victorialslocum_from-context-engineering-to-embeddings-chunking-activity-7355881903255658496-C_Jo/10mo2026-06-252026-06-25From context engineering to embeddings, chunking might be the most underrated part of the pipeline. It has more of an impact on performanceclippingsSoftware/Clippings/Chunking Strategies.md
Defer, Panic, and Recover - The Go Programming LanguageAndrew Gerrand 4 August 2010https://go.dev/blog/defer-panic-and-recover2010-08-032026-06-232026-06-23An introduction to the Go's defer, panic, and recover control flow mechanisms.clippingsSoftware/Clippings/Defer, Panic, and Recover - The Go Programming Language.md
Deploying Large Language Models — Tips & TricksManoranjan Rajguruhttps://medium.com/@manoranjan.rajguru/deploying-large-language-models-tips-tricks-8d9ef81bcf0b2023-09-272025-02-25 09:02:002025-02-26 23:02:69Hosting a large language model (LLM) can be a complex and challenging task. One of the main challenges is the large model size, which requires significant computational resources and storage…clippingsSoftware/Clippings/Deploying Large Language Models — Tips & Tricks.md
Don’t Build Multi-AgentsCognitionhttps://cognition.ai/blog/dont-build-multi-agents#principles-of-context-engineering2025-06-182025-06-182025-06-18Frameworks for LLM Agents have been surprisingly disappointing. I want to offer some principles for building agents based on our own trial & error, and explain why some tempting ideas are actually quite bad in practice.clippingsSoftware/Clippings/Don’t Build Multi-Agents.md
Go Slices: usage and internals - The Go Programming LanguageAndrew Gerrand 5 January 2011https://go.dev/blog/slices-intro2011-01-042026-06-232026-06-23How to use Go slices, and how they work.clippingsSoftware/Clippings/Go Slices usage and internals - The Go Programming Language.md
How to Design My First AI AgentFabiana Clemente, Towards Data Sciencehttps://towardsdatascience.com/how-to-design-my-first-ai-agent/2025-06-032025-06-112025-06-11The foundations of designing an AI agentclippingsSoftware/Clippings/How to Design My First AI Agent.md
How we built our multi-agent research systemAnthropichttps://www.anthropic.com/engineering/built-multi-agent-research-system?ref=blog.langchain.com2025-06-132025-06-182025-06-18On the the engineering challenges and lessons learned from building Claude's Research systemclippingsSoftware/Clippings/How we built our multi-agent research system.md
How's Linear so fast? A technical breakdownDennis Brotzkyhttps://performance.dev/how-is-linear-so-fast-a-technical-breakdown2026-05-022026-06-272026-06-27breakdown of the architecture behind Linear's speed: local-first sync, MobX observables, instant first loads, and a keyboard-first design.clippingsSoftware/Clippings/How's Linear so fast? A technical breakdown.md
Inside the Go Playground - The Go Programming LanguageAndrew Gerrand 12 December 2013https://go.dev/blog/playground2013-12-112026-06-222026-06-22How the Go playground works.clippingsSoftware/Clippings/Inside the Go Playground - The Go Programming Language.md
Is "IF" expensive?Stack Overflowhttps://stackoverflow.com/questions/315306/is-if-expensive2008-11-242025-02-10 14:02:002025-02-10 14:02:82I can't, for the life of me, remember what exactly our teacher said that day and I'm hoping you would probably know.The module is "Data Structures and Algorithms" and he told us something along theclippings, operatingsystemSoftware/Clippings/Is IF expensive.md
Life of an inference request (vLLM V1): How LLMs are served efficiently at scaleUbiCloudhttps://www.ubicloud.com/blog/life-of-an-inference-request-vllm-v12025-06-272025-06-302025-06-30vLLM is an open-source inference engine that serves large language models. We deploy vLLM across GPUs and load open weight models like Llama 4 into it. vLLM sits at the intersection of AI and systems programming, so we thought that diving into its details might interest our readers.clippingsSoftware/Clippings/Life of an inference request (vLLM V1) How LLMs are served efficiently at scale.md
LLM Distillation and Pruning: Maximizing EfficiencySapien IOhttps://www.sapien.io/blog/llm-distillation-and-pruning2024-10-252025-07-012025-07-01Learn all about LLM distillation and pruning strategies. Understand how these techniques optimize large language models for improved efficiency and performance.clippingsSoftware/Clippings/LLM Distillation and Pruning Maximizing Efficiency.md
LLM distillation demystified: a complete guideMatthew Casey, Snorkel AIhttps://snorkel.ai/blog/llm-distillation-demystified-a-complete-guide/2024-02-132025-06-302025-06-30LLM distillation isolates task-specific LLM performance and mirrors it in a smaller format—creating faster and cheaper performance.clippingsSoftware/Clippings/LLM distillation demystified a complete guide.md
PromptHub Blog: A Complete Guide to Meta PromptingDan Cleary, PromptHubhttps://www.prompthub.us/blog/a-complete-guide-to-meta-prompting2025-03-272025-06-102025-06-10Check out our deep dive on the latest meta prompting methods, like DSPy and TEXTGRAD, and the best prompt generator tools out there.clippingsSoftware/Clippings/Meta Prompting.md
PromptHub Blog: Exploring Multi-Persona Prompting for Better OutputsDan Cleary, PromptHubhttps://www.prompthub.us/blog/exploring-multi-persona-prompting-for-better-outputs2025-04-082025-06-102025-06-10See how a new prompting method can generate better results than standard and Chain of Thought (CoT) methodsclippingsSoftware/Clippings/Multi-Persona Prompting.md
Rewriting Bun in RustJarred Sumnerhttps://bun.com/blog/bun-in-rust2026-07-082026-07-092026-07-09Why & how we rewrote Bun from Zig to RustclippingsSoftware/Clippings/Rewriting Bun in Rust.md
The Agentic AI Handbook: A Beginner's Guide to Autonomous Intelligent AgentsBalajee Asish Brahmandam, FreeCodeCamphttps://www.freecodecamp.org/news/the-agentic-ai-handbook/2025-05-282025-06-192025-06-19You may have heard about “Agentic AI” systems and wondered what they’re all about. Well, in basic terms, the idea behind Agentic AI is that it can see its surroundings, set and pursue goals, plan and reason through many processes, and learn from expe...clippings, language/pythonSoftware/Clippings/The Agentic AI Handbook A Beginner's Guide to Autonomous Intelligent Agents.md
The Big LLM Architecture ComparisonSebastian Raschka, PhDhttps://magazine.sebastianraschka.com/p/the-big-llm-architecture-comparison2025-07-192026-06-282026-06-28From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture DesignclippingsSoftware/Clippings/The Big LLM Architecture Comparison.md
The Coding Assistant Breakdown: More Tokens PleaseMax Kan, SemiAnalysishttps://newsletter.semianalysis.com/p/the-coding-assistant-breakdown-more—2026-06-142026-06-14Hands On With GPT 5.5, Opus 4.7, DeepSeek V4, Why Benchmarks Are Bad, and Who’s Going To WinclippingsSoftware/Clippings/The Coding Assistant Breakdown More Tokens Please.md
The Open Source LLM Agent Handbook: How to Automate Complex Tasks with LangGraph and CrewAIBalajee Asish Brahmandam, FreeCodeCamphttps://www.freecodecamp.org/news/the-open-source-llm-agent-handbook/2025-06-032025-06-192025-06-19Ever feel like your AI tools are a bit...well, passive? Like they just sit there, waiting for your next command? Imagine if they could take initiative, break down big problems, and even work together to get things done. That's exactly what LLM agents...clippingsSoftware/Clippings/The Open Source LLM Agent Handbook How to Automate Complex Tasks with LangGraph and CrewAI.md
Understanding and Coding the KV Cache in LLMs from ScratchSebastian Raschkahttps://sebastianraschka.com/blog/2025/coding-the-kv-cache-in-llms.html2025-06-172025-06-302025-06-30I'm an LLM Research Engineer with over a decade of experience in artificial intelligence. My work bridges academia and industry, with roles including senior staff at an AI company and a statistics professor. My expertise lies in LLM research and the development of high-performance AI systems, with a deep focus on practical, code-driven implementations.clippingsSoftware/Clippings/Understanding and Coding the KV Cache in LLMs from Scratch.md
What are the differences between BPE and byte-level BPE?Stack Overflowhttps://datascience.stackexchange.com/questions/126715/what-are-the-differences-between-bpe-and-byte-level-bpe2024-02-042025-06-122025-06-12In Roberta, I'm not sure if the model use BPE or byte-level BPE tokenization, are these techniques different or the same ? Can someone explain ? ThanksclippingsSoftware/Clippings/What are the differences between BPE and byte-level BPE.md

Graph View

Backlinks