after a long wait
$XTEN TGE is finally happening on november 30
staking will also be live at TGE
The date is set.
XTEN launches on 30 November.
Sign the T&Cs before TGE to be included in the first XTEN transfer batch.
17
Sundrop Alpha retweeted
If you want to master production-level AI engineering, learn these 10 topics:
• Multimodal RAG: retrieve relevant information from text, images, audio and video
• Model selection: pick the right model for each task by cost, speed and quality
• Context engineering: give the model exactly what it needs, nothing more
• Agent orchestration: coordinate tools, agents and steps to finish real tasks
• Evaluation design: measure whether your AI is actually right not just fluent
• Fine-tuning: adapt a model to your data, tone or domain
• Inference optimization: make responses faster and cheaper at scale
• Observability: trace every call, cost and failure in production
• AI security: defend against prompt injection, data leaks and unsafe actions
• System design: build AI apps that stay reliable under real traffic
Demos impress people. Production pays.
Bookmark & Repost.
Sundrop Alpha retweeted
Make $2,000–$5,000/Month From GTA6 Without Owning PS5 or Spending $1
Full Tutorial:
00:00 $0 Investment
01:09 What Is Clipping ?
01:52 Tips for Creating Social Media Pages
02:42 Create video In this format
03:09 Finding Content Ideas
04:29 Create Unlimited Clipping Videos for free
09:42 How to Do It on Mobile
10:30 Tips to Grow Your Pages
12:10 How to make money
13:22 How to Automate Everything
Sundrop Alpha retweeted
this is a f*cking goldmine of AI prompts
prompts.chat/prompts
Sundrop Alpha retweeted
Coding games are the best way to learn coding.
From CSS, Python, JavaScript to Blockchain.
Here are 10 of the BEST online games to learn coding in 2026:
Sundrop Alpha retweeted
LLM Inference Engineering Roadmap
Part 1: Foundations
1. Training vs Inference
2. Inference Engineering
3. Closed vs Open Models
4. Latency vs Throughput
5. Model Selection
6. Model Evaluation (Evals)
Part 2: Transformers and LLM Architecture
1. Tokens
2. Token Embeddings
3. Positional Encoding
4. Transformer Architecture
5. Matrix Multiplication (Matmul)
6. Attention
7. Queries, Keys, Values
8. Causal Masking
9. Multi-Head Attention (MHA)
10. Feed-Forward Network (FFN)
11. Logits
12. Mixture of Experts (MoE)
13. Active vs Total Parameters
Part 3: LLM Inference Mechanics
1. Autoregressive Generation
2. Chat Templates
3. Context Window
4. Prefill vs Decode
5. KV Cache
6. Sampling
7. Temperature
8. Top-k Sampling
9. Top-p (Nucleus) Sampling
10. Stop Tokens
11. Reasoning Models
12. Token Streaming
Part 4: Performance Metrics
1. Time to First Token (TTFT)
2. Time Per Output Token (TPOT)
3. Throughput
4. End-to-End Latency
5. Latency Percentiles (P50, P90, P99)
6. Cost per Token
Part 5: Bottleneck Analysis
1. Compute vs Memory Bandwidth
2. Arithmetic Intensity
3. Roofline Model
4. Compute-Bound vs Memory-Bound
5. Prefill Bottleneck (Compute)
6. Decode Bottleneck (Memory)
7. Memory Footprint
8. KV Cache Memory Calculation
9. Batching and Arithmetic Intensity
Part 6: Hardware
1. CPU vs GPU
2. GPU Architecture
3. Tensor Cores
4. High-Bandwidth Memory (HBM)
5. DRAM vs SRAM
6. NVLink
7. InfiniBand
8. Groq LPU
9. Local (Edge) Inference
10. Cloud vs On-device Deployment
Part 7: Software Stack
1. CUDA
2. CUDA Kernels
3. CUDA Graphs
4. Kernel Fusion
5. PyTorch
6. Inference Engines
7. OpenAI-Compatible Server
Part 8: Benchmarking and Profiling
1. Performance Benchmarking
2. Traffic Simulation
3. Load Testing
4. Profiling
Part 9: Attention Optimizations
1. Standard Attention Inefficiency
2. FlashAttention
3. PagedAttention
4. Multi-Query Attention (MQA)
5. Grouped-Query Attention (GQA)
6. Sliding Window Attention
7. Attention Sinks
8. KV Cache Compression
Part 10: Batching and Scheduling
1. Batching
2. Static Batching
3. Continuous Batching
4. Batch Size vs Latency
5. Chunked Prefill
6. Prefill-Decode Interference
Part 11: Caching
1. Prefix Caching
2. Cache-Friendly Prompt Design
3. Prompt Caching
4. KV Cache Offloading
5. Cache-Aware Routing
6. Long Context Handling
Part 12: Speculative Decoding
1. Speculative Decoding
2. Rejection Sampling
3. Acceptance Rate
4. Draft-Target Speculation
5. N-gram Speculation
6. Speculation vs Batch Size
Part 13: Quantization
1. Quantization
2. Number Formats
3. Post-Training Quantization (PTQ)
4. Weight-Only Quantization (W4A16)
5. Weight-Activation Quantization (W8A8)
6. KV Cache Quantization
7. Measuring Quality Impact
Part 14: Model-Level Optimizations
1. Model Size vs Speed
2. LLM Routing
Part 15: Parallelism
1. Why Multi-GPU
2. Model Parallelism
3. Communication Overhead
4. Data Parallelism
5. Tensor Parallelism (TP)
Part 16: Disaggregation
1. Prefill-Decode Disaggregation
2. KV Cache Transfer
3. When to Disaggregate
Part 17: Production Infrastructure
1. Replicas
2. Autoscaling
3. Cold Starts
4. Observability
Start here: github.com/amitshekhariitbhu…
Sundrop Alpha retweeted
AI Engineer's thank me later:
1)github.com/microsoft/ML-F…
2) github.com/microsoft/AI-F…
3) github.com/karpathy/nn-ze…
4)github.com/labmlaiannotat…
5) github.com/GokuMohandas/M…
6)github.com/HandsOnLLM/Han…
7)github.com/NirDiamant/RAG…
Sundrop Alpha retweeted
99% AI. Hope you enjoy!
Lyrics: Me + Claude Opus 5.5
Image Stills: Midjourney v8
Video: Minimax H3
Editing: Me + Davinci + Claude Opus 5.5
Music: Suno v6 wild
Sundrop Alpha retweeted
The XTEN allocation checker and T&Cs are now live.
Eligible Xpoints holders can sign the Terms in the Extended app to see their XTEN allocation.
Signing window: 11 November 2026 to 31 December 2026, 23:59 UTC.
Starknet accounts must nominate a self-custodial EVM wallet with an active Extended account to receive XTEN. The TGE date will be announced separately.
Sign only in the Extended app: extended.exchange/
If I had $500k in crypto now, I would:
1. Go full-time crypto. Move somewhere cheap. One year to make it.
2. No BTC, no ETH, no SOL, no HYPE.
3. No memecoins. No directional leverage.
4. Allocate $250k to a delta-neutral strategy between @tradexyz and @metricxyz.
-> Short equity perps trading at a premium on tradexyz, buy the matching tokenized equities on metricxyz.
One strategy, three potential airdrops: HL S3 + tradexyz + metricxyz.
5. Allocate $50k to prediction markets on HIP-4. Market make tradfi outcomes. If options launch, be ready to arb them against a broker from day one.
6. Deposit and loop $200k of sUSDe on Aave.
-> Deposit sUSDe, borrow USDC, swap into more sUSDe. Use the net yield and some of the principal to cover living expenses.
Rotate into @acier, an upcoming lending protocol, when it's live.
7. Build AI apps on @flop_labs during testnet.
-> Vibe code your own apps. Use free testnet inference to get your first users and position yourself for the FLOP agent airdrop.
The goal: stay consistent and optimistic while positioning myself for potentially huge airdrops.
One year. Locked in.
Sundrop Alpha retweeted
Stake XTEN and trade for less.
From TGE, staked XTEN can earn staking rewards, and staking 500 XTEN or more places you in the League, which unlocks:
- Trading fee discounts from 5% to 30%
- Vault Extra Yield Boost from 0.5x to 5x, paid on up to $2,000,000 of your deposit.
- Affiliate payouts multiplied by up to 1.4x
Watch how the League works, then pick your piece.
Sundrop Alpha retweeted
Agents can now control phones.
Introducing Phone Harness (YC F26)
Let your agent use your personal phone, or its own iPhone/Android in the cloud
> Test and use real mobile apps
> Message and call people
> Grab verification codes for 2FA
Open source. Connect through MCP, CLI, or API.
Get started at phone-harness.com
Sundrop Alpha retweeted
AI engineers thanks me later.
github.com/patchy631/ai-engi…
Sundrop Alpha retweeted
🚨 غوغل تطلق مجاناً السلاح السري الذي يستخدمه آلاف مهندسيها يومياً لمنع الذكاء الاصطناعي من كتابة أسرع كود مليء بالأخطاء! 🧵
الأداة تُدعى "Elephant-Goldfish Model"، وفكرتها بسيطة لكنها عبقرية بشكل لا يُصدق:
❌ لا كود يُكتب حتى تكتمل الخطة ويصمد التصميم!
❌ لا يُسمح للذكاء الاصطناعي بتقييم عمله بنفسه!
❌ لا ضياع للسياق في منتصف المشروع!
إليك كيف تُدار اللعبة داخل غوغل 👇
🧠 الفيل (Elephant):
جلسة ذكاء اصطناعي واحدة طويلة المدى، تتذكر كل شيء: المعمارية، الهدف، والقرارات الصغيرة. دورها: تحاورك، تناقشك، وتُوثّق كل تفصيلة.. لكنها لا تكتب سطراً واحداً من الكود!
🐟 السمكة الذهبية (Goldfish):
جلسات ذكاء اصطناعي جديدة كلياً وبلا أي ذاكرة، لا تعرف شيئاً عن نقاشاتك السابقة حتى لا ترث أخطائك الذهنية أو تحيزك.
🔄 كيف تعمل هذه المنظومة العبقرية؟
1️⃣ العصف الذهني: مناقشة بينك وبين "الفيل" بحظر تام لكتابة الكود.
2️⃣ المسودة: صياغة وثيقة تصميم دقيقة تسبق التنفيذ.
3️⃣ اختبار الفهم : تطلب من "سمكة ذهبية" إعادة شرح التصميم، إذا أخطأت، يُعتبر المستند غامضاً ويُعاد صياغته!
4️⃣ الهجوم المضاد: عدة أسماك ذهبية تهاجم التصميم كمراجعين ماليين للبحث عن الثغرات والحالات الخاصة.
5️⃣ القرار النهائي: سمكة ذهبية أخيرة تعطي الضوء الأخضر بناءً على وضوح مسارات الملفات والـ Signatures.
🔥 لماذا يُعد هذا الأمر تحولاً جذرياً؟
يقول فريق غوغل: "الذكاء الاصطناعي جعل كتابة الكود أسرع، لكنه عجّل أيضاً بنشر الأكواد العشوائية والأخطاء. السرعة بلا حواجز حماية مجرد مضاعفة لأخطائك".
هذا النموذج يعكس الآية: يتم تدمير واختبار التصميم واكتشاف عيوبه قبل كتابة سطر كود واحد!
💡 الخبر الأفضل: الأداة مفتوحة المصدر مجاناً (ترخيص Apache 2.0)، وتتضمن كافة القواعد وشخصيات المراجعين. (ملاحظة: تعمل حالياً داخل Antigravity مع دعم باقي البيئات قريباً).
📌 احفظ التغريدة للرجوع إليها 🔖
رابط المستودع على GitHub تجدونه أسفل التغريدة 👇
Sundrop Alpha retweeted
If I had to land a $200K AI engineer job in 90 days, I would not get a degree.
I would master these 10 GitHub repos.
1. awesome-llm-apps
The production AI playbook. RAG, agents, multimodal apps, all in working code. 106K+ stars.
Repo → github.com/Shubhamsaboo/a…
2. LangChain
The foundational framework. Used in production by Klarna, Replit, Elastic, and most AI startups in 2026.
Repo → github.com/langchain-ai/l…
3. LangGraph
The orchestration layer powering production agents. The skill on every senior AI engineer job description.
Repo → github.com/langchain-ai/l…
4. CrewAI
Multi-agent coordination. The framework most Fortune 500 teams reach for first.
Repo → github.com/crewAIInc/crew…
5. Ollama
Run any open-source LLM on your own machine. The fastest way to learn how models actually work.
Repo → github.com/ollama/ollama
6. awesome-mcp-servers
MCP is the standard every major AI lab adopted in 2026. Knowing it puts you ahead of 99% of engineers.
Repo → github.com/punkpeye/aweso…
7. Qdrant
The vector database used for production RAG at scale. Embeddings and semantic search are non-negotiable for AI roles.
Repo → github.com/qdrant/qdrant
8. AI-Agents-for-Beginners
Microsoft's free 12-lesson course on building agents. Real code, real exercises, real prep.
Repo → github.com/microsoft/ai-a…
9. system-design-primer
Production AI is system design. The repo FAANG engineers use to prep for interviews.
Repo → github.com/donnemartin/sy…
10. awesome-claude-code
The playbook for the tool now used inside FAANG, OpenAI, Anthropic, and most YC startups.
Repo → github.com/hesreallyhim/a…
Here's the wildest part:
A $200K AI engineer in 2026 isn't paid for a degree.
They are paid for what these 10 repos teach.
The market doesn't care where you learned it. It only cares if you can ship.
90 days. 10 repos. One portfolio that proves you can do the work.
That's it. That's the whole game.
Save this before you forget.
100% free. 100% open source.
Sundrop Alpha retweeted
Learn AI for free directly from top companies.
1 - Anthropic:
anthropic.skilljar.com
2 - Google:
grow.google/ai
3 - Meta:
ai.meta.com/resources/
4 - NVIDIA:
developer.nvidia.com/cuda
5 - Microsoft:
learn.microsoft.com/en-us/tr…
6 - OpenAI:
academy.openai.com
7 - IBM:
skillsbuild.org
8 - AWS:
skillbuilder.aws
9 - DeepLearning.AI:
deeplearning.ai
10 - Hugging Face:
huggingface.co/learn
Comment "Learning" if you find this helpful.
Repost so others can take help.
Must bookmark for future reference.
Must Follow @sripathiteja4 for more
Sundrop Alpha retweeted
Forward Deployed Engineer Roadmap - A step-by-step roadmap to become a Forward Deployed Engineer (FDE) in AI, with a blog for every topic.
Start here: github.com/amitshekhariitbhu…
Sundrop Alpha retweeted
My roadmap to becoming an AI / Agentic Engineer as a Backend Engineer. 🚀
I'm done with just watching tutorials. I want to build the systems behind AI agents, from a simple CLI tool to production-grade agent infrastructure.
Here are 16 projects I plan to build, from beginner to advanced:
1. LLM CLI
Build my own terminal AI assistant with streaming, conversation history, model switching and token tracking.
2. CLI Coding Agent
An agent that can read my codebase, search files, explain bugs, propose fixes and run tests with my approval.
3. Local Agent Runtime
Build a reusable execution engine with tool calling, Pydantic validation, execution limits and error handling.
4. Codebase Intelligence CLI
Index repositories and answer questions about architecture, dependencies, function calls and potential code changes.
5. Engineering Workflow Copilot
Automate repetitive tasks like reviewing Git diffs, debugging failing tests, generating migration checklists and preparing PR descriptions.
6. MCP Server & Tool Gateway
Expose developer tools through MCP, with authentication, permissions, rate limits and audit logs.
7. Async Agent Orchestrator
Use FastAPI, asyncio and queues to execute hundreds of concurrent agent tasks with retries, timeouts and failure recovery.
8. Multi-Agent Swarm Runtime
Build Planner, Researcher, Coder and Reviewer agents that coordinate through typed state and structured handoffs.
9. Agent Observability & Replay Engine
Trace every LLM call, tool execution, state transition, latency, token usage and failure.
10. Agent Evaluation Framework
Create tests for agent behavior, replay trajectories and catch regressions in tool calls, safety checks, accuracy and cost.
11. Sandboxed Agent Execution
Give agents isolated environments to write code, run tests and inspect results without unrestricted access to my machine.
12. AI Inference & Agent Control Plane
Build model routing, rate limiting, concurrency controls, cost budgets, fallbacks and circuit breakers.
13. Memory & Context Engine
Implement working memory, session summaries, semantic retrieval, token budgeting and automatic memory eviction.
14. Human-in-the-Loop Workflow Engine
Pause long-running workflows, request approval through Slack, persist state and resume execution after approval.
15. Agent Security Gateway
Enforce tool permissions, handle untrusted instructions, protect agent-to-agent communication and maintain audit trails.
16. Shadow Execution & Fallback Runtime
Compare new agent versions against production-like inputs without side effects, and explore browser automation when API integrations fail.
The plan is to start small and progressively build more advanced systems.
I'll use Python, FastAPI, PostgreSQL, Redis, Docker, Temporal and agent frameworks where they make sense.
The goal isn't to build 16 random demos.
It's to understand how AI systems actually work under the hood: tool calling, memory, orchestration, concurrency, evaluation, security and reliability.
I'll document the architecture, trade-offs, failures and lessons from each project as I build.
Starting soon. Building in public. 🚀
If you're also transitioning from backend engineering to AI engineering, what would you build first?



























