Optimization Overview — SGD, Adam, LR Schedules & Scaling Rules | MIT 6.7960 Topic Guide
From SGD to Adam: pick the right optimizer and scale LR with batch size using scaling rules
tech
529 postsPS1 Walkthrough: From NumPy MLP to PyTorch Autograd Backprop | MIT 6.7960 Assignment 1
Hand-write NumPy MLP + backprop → verify with PyTorch Autograd, fully reproducing OCW HW1 core concepts
Regularization in Practice — Weight Decay, Dropout, Batch Norm & Label Smoothing | MIT 6.7960 Topic Guide
Regularization isn't just anti-overfitting — mechanisms & combo strategies for WD, Dropout, BN, Label Smoothing
Sandbox as a Standalone Commercial Product: Modal's $300M ARR Lesson
The business post (order 27) of the Sandbox Series. How Modal's sandbox grew from a feature to a $300M–$1B annualized run rate standalone product line, pricing and packaging strategies, and implications for build-vs-buy decisions.
Financial & Healthcare Compliance for Sandboxing
The security post (order 24) of the Sandbox Series. Compliance requirements for regulated industries (finance, healthcare) using sandboxes — SOC 2, HIPAA, GDPR, ISO 27001, EU AI Act — audit process, data sovereignty, and cross-border restrictions.
Sandbox Cost Model: Wall-Clock vs Active-CPU Billing
The cost post (order 26) of the Sandbox Series. Compares wall-clock vs active-CPU billing models, cost differences across isolation layers, and how to estimate monthly cost and avoid hidden fees.
Sandbox Lifecycle Management: Pause, Resume, Snapshot, Hibernation
The business post (order 28) of the Sandbox Series. Sandbox lifecycle management: pause/resume, snapshot/hibernation, resume concepts, implementation, and applicable scenarios for long-running tasks.
Sandbox Observability & Audit Trails
The security post (order 23) of the Sandbox Series. How tool calls, file operations, and network requests inside sandbox execution build auditable trails, trace-level visibility, immutable logs, SIEM integration, and the delegation-chain identity gap.
AI Agent Cloud Sandbox Product Landscape & Selection Matrix
The cloud landscape post (order 7) of the Sandbox Series. Summarizes positioning, pricing, cold start, isolation strength, and applicable scenarios for E2B, Daytona, Runloop, Vercel, Cloudflare, Modal, AWS Bedrock AgentCore, Alibaba OpenSandbox, Azure Container Apps — with a selection decision matrix.
Sandbox Series Overview: AI Agent Execution Environment Reading Map
The overview entry point (order 0) of the Sandbox Series. Explains at which isolation layer untrusted agent code should run, which provider to pick, and how to configure permissions, credentials, and network boundaries; technical details live in eight sub-series, this post is the map only.
Self-Hosted Sandbox: Kata Containers, Kubernetes agent-sandbox, BYOC
The self-hosted post (order 17) of the Sandbox Series. Kata Containers, Kubernetes-sigs/agent-sandbox, and BYOC model for enterprise self-hosted sandbox selection, architecture, and migration strategy, plus build-vs-buy decision framework.
WebAssembly Sandbox: Wasmtime, WasmEdge, Wasmer, and Pyodide
WebAssembly sandbox is the fourth-layer isolation option—lighter than containers, faster than microVMs. Wasmtime, WasmEdge, and Wasmer runtimes in 2026, Pyodide Python execution, and applicable scenarios with limitations.
Why You Shouldn't Let Agents Run Directly on Your Machine
The motivation post (order 1) of the Sandbox Series. Letting AI agents execute untrusted code carries direct risks: data exfiltration, privilege escalation, lateral movement, supply-chain poisoning, persistent backdoors. Sandboxing is not an optional add-on — it's the first line of defense.
How to Use Cloudflare AI Search: Data Sources, Hybrid Retrieval, and Workers Bindings
Formerly AutoRAG, the managed search primitive: drop files into built-in storage or attach R2 and websites, auto-index with Markdown conversion plus vector and BM25, retrieve with hybrid, RRF, and reranking, and query from Workers via namespace or instance bindings, REST, or MCP.
What Is GPUtw.ai? Taiwan GPU Cloud, Short-Rental Compute, and Researcher Workflows
GPUtw.ai is a Taiwan-based short-rental GPU cloud. Its main value is not maximum scale, but Taiwan data centers, prepaid credits, Jupyter/ComfyUI/Ollama/vLLM templates, Vault storage, and team billing. Public information is enough for a service introduction, not enough for procurement or production endorsement.
Why Did 'I Want a Beginner AI Course' Return Zero Results? Debugging Chinese Tokenization and a Broken RAG Data Path
Entering '我想找入門的ai課程' in Ask AI showed zero searched posts and triggered a refusal, while Related Reading recommended exactly the right article. The first fix addressed Chinese tokenization, the LIKE fallback, and the Vectorize data path. A second pass added short Han-and-number tokens, post metadata retrieval, and a rule that exposes sources only after both Validation and Critic pass.
Do These 4 Problems First — They Tell You What to Patch | Harvard CS181 Assignment 0
HW0 checks CS181 prerequisites in four problems — y=Xw solvability, optimizing an objective, reasoning about randomness, and OLS in Python. The problem that slows you down most is the gap to patch before HW1.
Ice Core Regression — kNN, Kernels, Basis Functions, and Regularization | Harvard CS181 Assignment 1
HW1 uses an 800,000-year ice-core temperature dataset across four problems: kNN and kernel regression, a geometric proof of least squares, basis-function regression, and a probabilistic derivation of ridge and LASSO, ending with a coordinate-descent LASSO implementation.
Your 2026 Roadmap Through 7 Homeworks (With a 4-Year Comparison) | Harvard CS181 Course Overview
CS181 2026 is A3 with hw0–6 as the weekly clock (no public recording links listed for the corresponding lectures); 2025 adds a practical, 2024 has two midterms, 2023 was taught by Weiwei Pan. Start with HW0, then follow hw1→hw6.
Search — From DFS, BFS, A* to Minimax and Alpha-Beta Pruning | Harvard CS50 AI Week 0
Week 0 is about search: DFS and BFS differ only in whether the frontier is a stack or a queue; A* adds the steps already taken to a heuristic estimate and guarantees the shortest path when the heuristic never overestimates; Minimax has the two players take the maximum and the minimum in turn, and alpha-beta pruning cuts branches that cannot change the result. With time links for every section, plus the approach, common mistakes and ways to check your work for the Degrees and Tic-Tac-Toe projects; the reference implementations are folded at the end of each project.