Little_Known

Software Engineering | Mobile Development | Data Science

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineer:

"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."

In 45 minutes she breaks down how Anthropic builds agents that remember, learn from their mistakes, and get smarter with every run.

Worth more than any paid course you'll find on building agents.

Watch the session, then read the guide on building loops below.

[Dhanian 🗯️ @e_opore]

Day 33/100 of Learning System Design.

Database Indexing and Query Optimization.

Grab the System Design Ebook: https://t.co/1pR2xx1I3p

[tut_ml @tut_ml]

Full Tutorial here- https://t.co/5ulBqIBJWA

[smrati tiwari @smratitiwa86867]

50 USEFUL GITHUB REPOS

1. iFixAi — AI misalignment testing
→ https://t.co/zny7t98k79

2. public-apis — free APIs for everything
→ https://t.co/x28IFXicmk

3. build-your-own-x — learn by building
→ https://t.co/xZSvMD9lqk

4. developer-roadmap — learn any tech skill
→ https://t.co/AC7qdZAfmL

5. free-programming-books — thousands of free books
→ https://t.co/YSnaCR1XRS

6. system-design-primer
→ https://t.co/i0fzEaUkSC

7. coding-interview-university
→ https://t.co/3eJcSFBs4c

8. the-art-of-command-line
→ https://t.co/xfSmOV7QHQ

9. project-based-learning
→ https://t.co/ct370oxIQo

10. you-dont-know-js
→ https://t.co/mabXy0i3aK

11. the-book-of-secret-knowledge
→ https://t.co/3Ulbfbimos

12. tech-interview-handbook
→ https://t.co/tYCef5QGUG

13. awesome-selfhosted
→ https://t.co/GTuF2QCq4i

14. javascript-algorithms
→ https://t.co/AI1L3j0pvQ

15. 30-seconds-of-code
→ https://t.co/APcOwzpCfP

16. github gitignore templates
→ https://t.co/JyXAJIYhkL

17. ollama — run LLMs locally
→ https://t.co/m9SS6VsPqp

18. langchain
→ https://t.co/z8gaRzO6TJ

19. n8n automation
→ https://t.co/ObvvsIjD92

20. openclaw — local AI assistant
→ https://t.co/0EdOWBKsd2

21. dify — AI app builder
→ https://t.co/rnjT65QkRQ

22. langflow
→ https://t.co/M6nDdVNpzQ

23. mem0 — AI memory layer
→ https://t.co/FBKGSue6jV

24. browser-use
→ https://t.co/HvSZcFydHr

25. crewAI
→ https://t.co/PnCB6T3bLH

26. MetaGPT
→ https://t.co/1dflqYE16Q

27. AutoGen (Microsoft)
→ https://t.co/ilJkBjqd2o

28. aider — AI coding assistant
→ https://t.co/KEQxJBjuWj

29. markitdown (Microsoft)
→ https://t.co/nBksZhBf4U

30. open-webui
→ https://t.co/LkGTJsWnsH

31. maigret — OSINT tool
→ https://t.co/HmBFo0qH4Y

32. TradingAgents
→ https://t.co/pBHFcUrvQV

33. stagehand
→ https://t.co/JoxTWByyWP

34. firecrawl
→ https://t.co/A5mosuslTo

35. transformers (HuggingFace)
→ https://t.co/aBCeFYrc1b

36. vLLM
→ https://t.co/pg3Tjhm9gs

37. llama.cpp
→ https://t.co/A2ZPPdRMsy

38. llama_index
→ https://t.co/7YHqyfyyIB

39. nanoGPT (Karpathy)
→ https://t.co/gKPFti6WEs

40. RAGFlow
→ https://t.co/lFfVh4LyWr

41. supermemory
→ https://t.co/oZpcvGE4y4

42. awesome-claude-skills
→ https://t.co/pg9qFngiFv

43. Bumblebee (Perplexity AI security tool)
→ https://t.co/lkxw3TsoZP

44. ComfyUI
→ https://t.co/8F4QTPDWk2

45. DeepSeek (official repo varies by model release)
→ https://t.co/Qu8XmAXWS7

46. Lobe Chat
→ https://t.co/CgLNkrKdPx

47. freeCodeCamp
→ https://t.co/C5akezcUfu

48. system design + interview prep extras (bonus)
→ https://t.co/3eJcSFBs4c

49. AI agents ecosystem (extra)
→ https://t.co/z8gaRzO6TJ

50. automation + AI workflows (extra)
→ https://t.co/ObvvsIjD92

Save this before you forget it exists.

You'll come back to at least ten of these.

[smrati tiwari @smratitiwa86867]

10 GitHub repos that are quietly helping people build income on autopilot.

Most people will never find these.

1. Claude Ads
https://t.co/Z0kYJ3lg3U

2. Agentic Inbox
https://t.co/H2jAaCvcdZ

3. AutoHedge
https://t.co/1FwVJXSpDU

4. Hyperframes
https://t.co/aG9fhquHCY

5. Vibe Trading
https://t.co/JZzVzXJLoG

6. Open Higgsfield AI
https://t.co/KLx0FGVQWZ

7. Fincept Terminal
https://t.co/XXEFy9VWFa

8. Camofox Browser
https://t.co/o1146eF4av

9. Claw Router
https://t.co/76gKmP83uZ

10. NotFair
https://t.co/VytTNjVhfU

Bookmark this.

Follow me for more open-source AI tools that give you an unfair advantage.

[Peller_DA📊 @peller02]

Hi, #DataFam! 👋

It's a new week and a new hurdle to analyze. Let's make it an amazing and productive week!

#PowerBI #SQL #DataAnalytics

[TheStoicCode @X_TheStoicCode]

14 TÉCNICAS DE HARVARD para ser mejor que el 99% de las personas

1. La regla de los 5 segundos

[DAN KOE @thedankoe]

https://t.co/kfa0CkvdgU

[Phosphen @phosphenq]

This might be the most dangerous 37 pages in AI right now.

Cambridge and NVIDIA just dropped the blueprint for agents that improve themselves, with no human in the loop.

This is the leap every lab is racing toward: an AI that rewrites itself and gets sharper every run.

Bookmark it before it's everywhere. Loop engineering guide below.

[Khairallah AL-Awady @eng_khairallah1]

this is f*cking gold

How to build your first AI agent (Full guide)

if I had this a year ago, I would've shipped my first agent in a day instead of 2 weeks

in the right hands, this changes everything:

[Andrew @s4yonnara]

Andrej Karpathy spent 70 minutes breaking down how top AI users actually work with LLMs.

The reality is simpler than people expect. You tell the model what you want in plain language and let it run.

No 40-line system prompts. No secret tricks.

By 2026 the engineer who writes off LLMs loses to the junior who just set one up properly.

70 minutes. Free. A rare straight look from an OpenAI co-founder.

Bookmark it and watch.

[Akshay 🚀 @akshay_pachaar]

Web scraping will never be the same.

(100% open-source visual search at scale)

PixelRAG is a retrieval system that skips HTML parsing completely.

Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels.

Why that matters: parsing is where web RAG quietly loses information.

- A single HTML-to-text parser can drop 40%+ of a page.
- Tables, charts, and layout get flattened or thrown out.
- Swapping parsers alone can move accuracy ~10 points on the same docs.

PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA.

The repo also ships a Claude Code plugin that gives Claude eyes.

It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like.

One setup script. No MCP server, no backend.

How the pipeline works:

- Renders each document (web, PDF, image) to image tiles.
- Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots.
- Builds a FAISS index and serves a search API.

A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels.

Everything is open-source under Apache-2.0.

GitHub repo: https://t.co/qun9TjAdmw

Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x.

The article is quoted below.

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents

40 minutes from the team behind Claude Code

they used three agents: one to plan, one to build, one to judge, cycling until the app actually works

the winners won't have the smartest model, they'll have the best loop

watch it, then read the full guide on how to actually use loops below

[Trader Theory @tradertheory]

How I get ready to trade my $100 personal account:

[Manchester City @ManCity]

Our 2026/27 @premierleague fixtures 📋🙌

[Akshay Shinde @ConsciousRide]

90% of AI Engineering interviews in 2026 come down to these 7 points.

1. LLM Fundamentals: tokenization, transformers & attention, fine-tuning (LoRA/QLoRA), context management, model selection

2. RAG Systems: chunking strategies, embeddings, vector databases, retrieval & reranking, hallucination mitigation

3. Agentic Workflows: tool calling & function calling, ReAct/Plan-Execute patterns, memory & state, multi-agent orchestration

4. Inference Optimization: quantization (AWQ/GGUF), serving engines (vLLM/TGI), batching & KV cache, latency vs cost tradeoffs

5. Evaluation & Observability: LLM-as-judge evals, custom metrics, A/B testing, drift detection, prompt/response logging

6. MLOps Pipelines: experiment tracking, model versioning & registries, CI/CD for AI, data pipelines, deployment automation

7. Production Realities: safety guardrails & prompt injection, scaling inference, cost optimization, debugging failures, compliance & reliability

[Master Your Mind @MasterrYourMind]

The 14 best psychology tricks only the top 1% know

-Thread-

[Geronimo Morgans @GeronimoMorgans]

Gvardiol takes us through:

1) What it took to get back from that injury against Chelsea last season (the one that kept him out for four months).

2) The relationship and friendship he has with Kovačić.

3) His thoughts on Khusanov and the lad's talent.

4) What the Manchester City dressing room is really like.

5) Whether he'd like to be the future captain for both club and country.

Good watch this. Proper insights.

[Rahul @sairahul1]

Anthropic pays $750,000+ a year for engineers who can build LLMs from scratch.

Not how to prompt them.
Not how to fine-tune them.
Not how to build RAG pipelines.

But how to build them from scratch.

This 2-hour Stanford lecture teaches you everything.

Scaling laws.
Data collection.
Architecture design.
Post-training alignment.

Free. From Stanford.

Watch first. Then read this.

The lecture is the theory.

And this article shows you how to actually build it (with code) ↓

[Abraham Okah(info hub) @AbrahamOkah2]

cybersecurity from a beginner to an expert.

https://t.co/oRQ03NkU48