Puvi

[Rahul @sairahul1]

Top 10 YouTube channels to learn AI from scratch:

1) Andrej Karpathy – Deep yet accessible lectures on deep learning, LLMs, and an intro course on neural networks. https://t.co/QBpPHlrgh0
2) 3Blue1Brown – Stunning visualizations that make abstract mathematical concepts intuitive. https://t.co/kkWfM9JhCL
3) Lex Fridman – In-depth conversations with AI leaders, offering a broader perspective on the field. https://t.co/pZA5PeH01Y
4) Machine Learning Street Talk – Technical deep dives and discussions with top AI researchers. https://t.co/1qnEeHV9hi
5) StatQuest with Joshua Starmer PhD – Beginner-friendly explainers on machine learning and statistics. https://t.co/VP0PceT4Yz
6) Serrano Academy (Luis Serrano) – Clear and accessible content on ML, deep learning, and AI advancements. https://t.co/HARB8EQ9Oc
7) Jeremy Howard – Practical deep learning courses and AI-powered web app tutorials. https://t.co/BmHqGwQxvB
8) Hamel Husain – Hands-on lessons in LLMs, RAG, fine-tuning, and AI evaluations. https://t.co/kOndFF0b1S
9) Jason Liu – Expert-led lectures on RAG and AI freelancing tips for ML developers. https://t.co/nrbvujlUwi
10) Dave Ebbelaar – Practical guides on building AI systems and real-world applications. https://t.co/VuTtSgrfv4

[Suraj Sharma @suraj_sharma14]

As an AI Engineer, you must build these projects.

Systems that prove you can ship production AI.

1.) Production RAG with Citations
PDF Q&A bot that cites page numbers, implements hybrid search, reranking, and grounding.
Stack: LangGraph + SQLite-vec + cross-encoder.

2.) Cost-Optimized Model Router
System that routes queries by complexity to cheap/expensive models, tracks spend per request. Stack: LiteLLM + Prometheus + custom router.

3.) Multi-Agent Research System
Supervisor coordinates researcher, writer, fact-checker with consensus logic and human approval gates.
Stack: CrewAI + audit trail.

4.) Automated Eval Harness
Runs 100+ golden test cases before every deploy, blocks regressions, tracks quality trends.
Stack: DeepEval + RAGAS + LangSmith.

5.) Real-Time Observability Dashboard
Distributed tracing, cost per request, latency percentiles, error rates, alerting on anomalies.
Stack: OpenTelemetry + Grafana + Prometheus.

6.) Security Guardrail Middleware
Detects prompt injection, redacts PII, filters outputs, enforces rate limits, sandboxed execution.
Stack: Guardrails AI + custom rules.

7.) Local-First Development Environment
Ollama + SQLite-vec + FastAPI, zero API costs, offline testing, mirrors production architecture.
Stack: Ollama + LanceDB + Docker.

8.) Streaming Copilot UI
Real-time token streaming, optimistic UI updates, graceful degradation on latency, error recovery.
Stack: Next.js + Vercel AI SDK.

9.) Fine-Tuning Pipeline with LoRA
Dataset preparation, instruction tuning, DPO alignment, evaluation before/after, catastrophic forgetting prevention.
Stack: PEFT + Hugging Face.

10.) Multi-Tenant SaaS Agent
User isolation, per-tenant rate limiting, usage-based billing, data partitioning, audit trails.
Stack: Supabase + Stripe + LangGraph.

11.) CI/CD for AI Systems
GitHub Actions, automated testing, canary deployments, automatic rollback on quality drop, feature flags.
Stack: GitHub Actions + ArgoCD.

12.) Vector Database at Scale
Hybrid search, metadata filtering, embedding caching, index optimization, backup/recovery procedures.
Stack: Qdrant or Weaviate.

13.) Agent Memory System
Short-term buffers, long-term recall, context compression, cross-session sync, memory eviction policies.
Stack: Redis + vector DB.

14.) Production Inference Server
vLLM or SGLang deployment, KV cache optimization, continuous batching, quantization, load balancing. Stack: vLLM + Kubernetes.

15.) Human-in-the-Loop Workflow
Uncertainty detection, approval UI, pause/resume logic, validated context, full audit trail.
Stack: LangGraph + custom UI.

16.) Agentic Automation Pipeline
Webhooks, async execution, idempotency, dead-letter handling, retry logic with exponential backoff.
Stack: FastAPI + Celery.

17.) Domain-Specific Benchmark
Create eval suite for legal, medical, finance, or code. Public leaderboard, community adoption.
Stack: Custom + pytest.

18.) Open Source Contribution
Extend LangGraph, CrewAI, or LlamaIndex. Fix bug, add feature, write docs, publish benchmarks.
Stack: Your choice.

happy building...

Bookmark & Repost!

[Puvi @puvii_10]

@VigneshKPhoenix Dialogue ah maathunga da

Ketu ketu pulichi pochi

[Puvi @puvii_10]

@Bacteria_Offl tomorrow morning assembly ku vara sollu

Thoongida poranga

Makkal ah illa thookam ah nu tomorrow therinjidum

[Puvi @puvii_10]

@NishitShawHere Karuppu

It is literally a scrap movie

[Puvi @puvii_10]

@SunTV @rajinikanth @Nelsondilpkumar @anirudhofficial @vijaykartikdop @Nirmalcuts @ChethanDsouza @AlwaysJani @KiranDrk @valentino_suren @kabilanchelliah @RIAZtheboss @anirudhofficial once again proved he is the 🐐 🔥🔥🔥