Page 55 of 129
Week 2 connects model internals to retrieval engineering: decoding, attention, training, inference and context budgets in Lecture 02; chunking, indexes, sparse/dense retrieval, reranking and agentic RAG in Lecture 03. Separate reading digests examine workflow selection and the RAG and ColBERT experiments.
Lecture 04 follows tool use from training and API retrieval to function calling, MCP and reliability evaluation. Lecture 05 compares DSPy, LangGraph, harnesses, Temporal and observability. Separate MCP and DSPy reading digests explain the protocol and optimization mechanisms; HW1 remains a hand-built harness.
Week 4 connects the ReAct loop and MemGPT memory hierarchy to Lecture 06/07: composing design patterns, keeping context focused without losing commitments, choosing memory architectures, and evaluating correct use. An original email-assistant example tests whether compaction preserves an approval constraint.
Lecture 08 explains orchestration, communication, task ledgers and worktree isolation. Lecture 09 starts with data and evaluation, then compares context optimization, SFT, RL and distillation. Use a traceable email example to decide whether collaboration or optimization addresses the actual bottleneck.
Week 6 connects Terminal-Bench outcome verification with Shankar’s data flywheel: check what the agent actually changed, turn reviewed failures into development examples, and keep independent test tasks separate. HW1 is due October 30.
Week 7 is midterm checkpoint week: data selection on Monday, evaluation and benchmark design on Wednesday. Zhu et al. teach you not to be fooled by your own scores, SWE-smith scales software-engineering tasks to 50,000 instances, and you close by drafting a first 4-tuple for HW2.
Week 8 builds model judges with MT-Bench and Anthropic's eval guide on Monday, then faces production leakage with PrivacyLens and four guardrails on Wednesday. The paper video is due Friday, and this week's deliverable is one working judge score plus one permission check.
Week nine turns to coding agents: SWE-agent shows interface is performance, OpenHands packs sandbox plus benchmarks into one general base, and the second homework is due Friday — ship one working bug-fix exam this week.
Four AI security certs, four different bets: SecAI+ ($298) is CompTIA's mid-level expansion play, CAISP ($1,099 all-in) has the strongest hands-on labs and fullest OWASP LLM Top 10 coverage, GAIPS ($999/$9K) is the SANS gold-standard defender cert with CyberLive exams, and AAISM ($459+) is governance-layer but requires CISM or CISSP first. Under $400 → SecAI+. Want to actually hack and fix → CAISP. Company paying → GAIPS. For the offensive side (AI red teaming), OSAI+, HTB COAE, and COASP launched in 2026 and form their own group; see the section near the end.
10+ new AI security certifications launched in just 18 months (2025–2026), while the classic trio — Security+ ($439), AWS Security Specialty ($300), CISSP ($749) — remains foundational. For AI platform developers who aren't security specialists, a three-phase path works best: Security+ → AWS Security → SecAI+ or CAISP → CISSP, totaling $1,780–$2,700.
Security+ ($439) takes 2–3 months, no published pass rate, +$10K–$20K salary premium. AWS Security Specialty ($300) takes 2–3 months, 45–55% pass rate, highest ROI at 40–67x. CISSP ($749) takes 3–6 months, 50–60% pass rate, +$25K–$35K premium but requires 5 years of experience. Five-year cost to earn and maintain (including estimated study materials): Security+ about $619, AWS Security $200–$350 (no annual fee), CISSP about $1,524.
Taiwan's Cybersecurity Act 2.0 passed and FSC's three-tier system is in place, but neither mandates specific certifications — real demand comes from the job market. Taiwan has 7+ training providers: Uuu has the widest catalog (classroom courses for all three of SecAI+, COASP, and OSAI+), WUSON is the CISSP legend (monthly cohorts sold out through mid-2027), and DEVCORE was the first to bring OffSec factory instructors. ISC2 test centers in Taipei and Kaohsiung; most certs also support online proctoring from home.
Start with the opening slides on the agent loop, components, and engineering challenges, then examine BAIR's compound systems, Ng's work patterns, and Si's execution-feedback experiments. Distinguish the lecture, required reading, and additional readings.
Start with the opening slides on the agent loop, components, and engineering challenges, then examine BAIR's compound systems, Ng's work patterns, and Si's execution-feedback experiments. Distinguish the lecture, required reading, and additional readings.
GPUtw.ai makes sense as a short-rental GPU learning tool: start with Jupyter, Ollama, or ComfyUI, then try LoRA/QLoRA on a small model. It is not a large foundation-model training platform, and the first run should verify deployment, billing, and data retention with a small budget.
Marker (Datalab open source, Apache 2.0 license, v2.0.0 released 2026-07-20, 39.5k stars) is a pipeline-style document parsing standard library that outputs Markdown and JSON, supports optional LLM boost (`--use_llm`, default `gemini-3.5-flash`), custom formatting logic, table/formula/inline-math/link/reference/code formatting, image extraction and preservation, header/footer removal, and runs on pure CPU, GPU, or MPS (`Apple Silicon`). Unlike [Docling](/posts/tech/2026-09-06-docling-document-parsing) (structured JSON core, dedicated XML exports, pure MIT), Marker centers on Markdown/JSON under `Apache 2.0` with a separate model-weight license (`AI Pubs Open Rail-M`, $5M commercial threshold); unlike [MinerU](/posts/tech/2026-09-05-mineru-ocr-doc-parsing) (custom agreement with MAU/revenue thresholds + attribution obligations), Marker offers a simpler licensing story (`Apache 2.0` code) but requires accepting a separate model-weight license for weights. The series framework ([three-layer model](/posts/ai/2026-08-06-document-parsing-three-layers)) positions all three (`MinerU`, `Docling`, `Marker`) as pipeline-based parsing-layer options with distinct licensing, output, and speed trade-offs.
A close look at three open-source projects training LLMs from scratch in the Chinese community — baby-llama2-chinese (218M, 63.4B tokens), ChatLM-mini-Chinese (0.2B T5, 10.23M dialogues), and Steel-LLM (1.12B, 1T tokens, 8 months) — comparing corpus strategy, tokenizer decisions, and community ecosystem. Honest evaluation included: baby-llama2 scored a bottom-ranking 21 in MiniMind's side-by-side test; ChatLM has the strongest knowledge (62) but weak coding.
Four coding agent TUIs all follow the same two rules: tools maintain constant height (one-line summary, never jumping from 0 to N lines) and never auto-collapse (only user-initiated expand/collapse). looplane violates both.
OpenELM uses layer-wise scaling to shift parameters toward layers near the output; with 1.08B parameters and 1.5T tokens it beats OLMo 1.2B (+2.36% on the LLM360 average) despite OLMo training on 3T tokens. MiniCPM trains multimodal small models from scratch with a three-stage unfreezing recipe (Resampler first, vision encoder next, everything unfrozen last); MiniCPM-V 4.5 reaches sub-30B SOTA on VideoMME with only 8B parameters, and 4-bit quantization squeezes fp16's 16–17GB memory footprint down to about 5GB for phones.
A tour of Karpathy's three teaching repos: nanoGPT (2022, ~300 lines each to reproduce GPT-2 124M), llm.c (pure C/CUDA training), and nanochat (2025-10, one speedrun.sh from tokenizer to WebUI). $100 and 4 hours on 8×H100 buys a chatty model; GPT-2-grade capability is now down to about 2 hours and $48.