Alejandro Mancilla

[Rahul @sairahul1]

Google just dropped a 1-hour course on agentic engineering from scratch:

00:00 – How to build your first AI agent
08:24 – Build agent memory (short, persistent, long)
28:34 – Agentic loops, long-running AI agents
40:04 – How to build MCP (MCP vs API)
1:00:22 – Multi-agentic systems

This 1-hour watch will replace 10 paid agentic courses on the internet.

Bookmark this. Watch this weekend.

[Alex Lieberman @businessbarista]

This is one of the best breakdowns on the fundamentals of LLMs I've ever read.

Anytime someone asks me for resources to climb the steep AI learning curve, I always provide the same list.

1) @3blue1brown's neural network videos
2) @karpathy's zero to hero playlist
3) @dwarkesh_sp's whiteboard explainers

Now @_raghavdixit_'s "Vectors are all you need" and future articles in the explainer series are getting added to the list.

[Morty @0xMortyx]

Andrej Karpathy: "90% of what AI twitter tells you to learn will be dead in 6 months"

90% of what ai twitter tells you to learn dies in 6 months

senior engineers already stopped chasing it

the dead list: autogen, crewai, autonomous agent pitches, agent marketplaces, benchmark leaderboards, semantic kernel, dspy as a general framework, horizontal "build any agent" platforms, per-seat pricing for agents

the pattern is obvious. demos that break in production. hype that never ships. frameworks that go viral on monday and vanish by spring

what actually compounds:
context engineering
tool design
orchestrator-subagent pattern
eval discipline
the harness mindset. harness > model, always
mcp as the protocol layer

the edge isn't the newest framework. it's staying a few steps ahead until your signal becomes everyone's mass-opinion

book and study this

[Rahul @sairahul1]

Andrej Karpathy's advice for beginners getting into AI:

"Put in 10,000 hours of work."

He's right.

But most builders waste the first 1,000 hours on the wrong things.

They write code before understanding context windows.
They build agents before understanding token limits.
They ship products before understanding what models can't do.

The builders who compound fastest aren't the ones who code the most.

They're the ones who understood the fundamentals before touching a single line.

These are the 10 concepts that make the first 1,000 hours count ↓

Bookmark this before you start.

[darkzodchi @zodchiii]

Shopify's Head of Engineering: "If you don't figure out how to harness agents in 2026, you'll be behind."

This interview is the most practical breakdown of enterprise AI coding I've seen this year.

Farhan Thawar explained the full Shopify AI playbook here.

Watch the interview, then grab the exact template below 👇

[Anatoli Kopadze @AnatoliKopadze]

the engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work

I've seen $300 courses that don't cover what he shows in the first 10 minutes

CLAUDE.md files, memory shortcuts, parallel sessions, prompting patterns

all in one video and completely free

works whether you're a developer, a beginner, or someone who's been using Claude for months

based on this, I put together 18 things you can copy and use in Claude today

full guide in the article below

[santi @santtiagom_]

Cuando varios agentes trabajan sobre el mismo código, aparece un problema nuevo:
cada uno puede interpretar el sistema de forma distinta.

Uno cambia una API. Otro refactoriza una lógica. Otro agrega una feature sin conocer ciertas restricciones.

Y el sistema empieza a perder coherencia.

Ahí es donde SDD (Spec-Driven Development) empieza a tener sentido.

La idea es definir antes:
cómo funciona el sistema, qué reglas existen y qué cosas no se pueden romper.

Por ejemplo, en un sistema de pagos, la spec puede definir:
- una transacción aprobada nunca puede volver a “pendiente”
- un reembolso no puede ser mayor al monto original
- solo ciertos servicios pueden modificar pagos

Entonces cualquier agente que trabaje sobre ese flujo comparte las mismas reglas y toma decisiones mucho más consistentes.

Y creo que eso es lo interesante de SDD:
convertir reglas y restricciones del negocio en una fuente de verdad compartida para agentes trabajando sobre el mismo sistema.

En parte, siento que la tarea del developer empieza a moverse hacia ahí:
menos tiempo escribiendo código manualmente y más tiempo definiendo cómo debería comportarse el sistema.

[Nav Toor @heynavtoor]

A guy in Karachi rebuilt GPT-4 in one Jupyter notebook.

OpenAI spent over $100 million to train the real one. He put the entire recipe on GitHub for free.

His README still says "I am looking for a PhD position in AI."

It's called Train LLM From Scratch. A working guide that walks you through building your own 2-billion-parameter language model on a single GPU.

OpenAI vs this repo:

- Training cost: $100M+ → Single A100 or RTX 4090 (you can rent for $1/hr)
- Code access: Closed → Open, MIT license
- Data: Secret → The Pile (open dataset, 825GB)
- Walkthrough: None → Every line of code explained, top to bottom
- Output quality: GPT-4 → A small model that writes broken English (but it's yours)

The whole thing fits in one notebook. No paid course. No paywall. No "Pro" tier.

What you actually learn:

→ How a transformer works, end to end
→ How to download and tokenize the Pile dataset
→ How to build multi-head attention from scratch in PyTorch
→ How to train on a single GPU without running out of memory
→ How to generate text from your trained model
→ How to scale from 13 million parameters to 2 billion

774 stars. 135 forks. MIT license. The full theory paper-to-code in one place.

One honest note: this is a learning repo, not a production model. Your output will be small and rough. But you will understand exactly how GPT-4 works after reading it.

Fareed Khan built this from Karachi, Pakistan. He has 1,780 GitHub followers. He's still looking for a PhD position. The recipe to billion-dollar AI is sitting on his profile, free.

This is what open AI was supposed to mean.

(Link in the comments)

[Vaishnavi @_vmlops]

HE CRACKED ML INTERVIEWS AT TOP COMPANIES WITH JUST 80 LEETCODE PROBLEMS

Grinding 500+ questions in panic… he chose a system instead

He focused only on the patterns that actually show up in ml rounds trees, graphs, dynamic programming, binary search, sliding window... that's it

but the real secret wasn't the list

it was his rule: solve every non-trivial medium 3 times

first time you struggle... that's fine second time you start seeing the pattern
third time you solve it in under 10 minutes

he tracked every session how long it took, how many attempts until the problems felt automatic

result...? offers from snapchat, coupang & stitchfix

not because he knew everything because he knew the right things deeply

the full list is free on github

https://t.co/6Eiplo7uye

[Rohit @rohit4verse]

andrej karpathy spent two hours teaching one thing: tokens are the atom of llms. tokenization is at the heart of every llm weirdness you've ever debugged.

[watch the 15-min clip below. then run the 7-day playbook]
↓ save this before everyone copies it

learn how the tokenizer works. understand how your llm actually consumes input. then run the engineering roadmap that took one production agent from $4,800/mo to $620/mo in 7 days.

87% reduction. no model swap. no framework migration. no quality drop on the eval set.

token cost in 2026 is an engineering discipline. every line of your system prompt is rent you pay forever.

what was eating the budget:

→ a single forgotten cron job ate 47% of one team's bill. they turned it off on a tuesday and the bill dropped before they wrote any optimization code.

→ anthropic ships a 90% discount on cache reads. one config line, cache_control ephemeral, break-even after one hit. most teams cache the volatile parts of the prompt and watch their hit rate sit at 12%.

→ one production agent went from 14,500 tokens of context overhead per turn to 850. a 94% drop. output quality held within 2% of the uncompressed baseline.

→ 60% of agent calls are haiku-tier work running on opus rates. classify the task first. pick the model second.

→ retry loops are the silent killer. no MAX_STEPS bound, one bad search query, $14 burned in a single session. one team traced 38% of their bill to this single pattern.

karpathy gave you the atom. the playbook below gives you the harness.

watch the lecture. read the playbook ↓

[Avid @Av1dlive]

Cursor pays engineers $1,100,000 a year to run teams of AI agents that ship code while they sleep.

[The CEO of Cursor explained in 9 minutes how they ship at 100x speed using team of agents]

↓ Save this before everyone copies the playbook

1. Engineers no longer babysit one assistant. They manage dozens of agent colleagues working in parallel, each on its own remote machine

2. Validation contract before code, not after. Humans only at scoping and review.

3. The agent team handles the full loop : planning, coding, testing, shipping PRs with each agent specialised for a role.

Watch the guide. Then read the guide below by @eng_khairallah1

[Khairallah AL-Awady @eng_khairallah1]

INSTEAD OF WATCHING NETFLIX TONIGHT.

Spend 2 hour with this.

Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything.

The people who watch this tonight will wake up tomorrow with a new skill.

Watch it and Bookmark it now.

[Avid @Av1dlive]

https://t.co/2Ada7jw3sa

[Avid @Av1dlive]

in 15 minutes, 2 Senior Staff Engineers at Airbnb gave a Live Lecture on Agentic Coding

Airbnb already shipped one of the most ambitious LLM-agent migrations in production.

Tonight two of their senior engineers shows how they actually build with agents in 2026.

Most builders are guessing. These guys ship.

bookmark & watch this.then read the complete article below.

[Rahul @sairahul1]

dev who spent 4 years in CS to spend 8 hours a day in meetings watching this 👀

[Abhishek Singh @0xlelouch_]

As a Senior Backend Engineer trying to move towards Staff, I can tell you one thing clearly:

At Senior level, knowing system design fundamentals is not enough anymore.

You are expected to design a good system.

At Staff level, you are expected to design the right system for the business, explain the tradeoffs, influence multiple teams, reduce long term operational pain, and make sure the system does not collapse when traffic, teams, and complexity grow.

So if you are already good at system design but still feel stuck at Senior, spend the next 3-6 months building these Staff Engineer muscles.

Architecture & Technical Strategy
↬ System boundaries
↬ Platform thinking
↬ Build vs buy decisions
↬ Monolith decomposition
↬ Multi-region architecture
↬ Migration strategies
↬ Backward compatibility
↬ API contracts
↬ Long-term maintainability
↬ Reducing operational complexity
↬ Designing for org structure
↬ Architecture decision records
↬ Technical roadmap planning
↬ Removing accidental complexity
↬ Identifying single points of failure
↬ Choosing boring technology
↬ Knowing when not to build
↬ Designing systems that teams can own

Scalability & Distributed Systems
↬ Caching strategy
↬ Queueing strategy
↬ Partitioning
↬ Sharding
↬ Replication
↬ Leader election
↬ Rate limiting
↬ Load shedding
↬ Backpressure
↬ Fan-out/Fan-in
↬ Idempotency
↬ Retry storms
↬ Consistency models
↬ Eventual consistency
↬ Distributed transactions
↬ Data locality
↬ Hot partitions
↬ Graceful degradation
↬ Capacity planning
↬ Failure mode analysis

Databases & Data Architecture
↬ Data modeling
↬ Indexing strategy
↬ Query patterns
↬ Read/write scaling
↬ OLTP vs OLAP
↬ CDC
↬ WAL
↬ Transaction isolation
↬ Schema evolution
↬ Data retention
↬ Backup and restore
↬ Archival strategy
↬ Hot/cold storage
↬ Multi-tenant data design
↬ Event sourcing
↬ CQRS
↬ Denormalization tradeoffs
↬ Data correctness
↬ Reprocessing pipelines
↬ Analytics vs product database separation

Reliability & Operations
↬ SLO/SLI/SLA
↬ Error budgets
↬ Alert quality
↬ Incident response
↬ Postmortems
↬ Runbooks
↬ On-call pain reduction
↬ Canary deployments
↬ Rollbacks
↬ Feature flags
↬ Disaster recovery
↬ Load testing
↬ Chaos testing
↬ Health checks
↬ Circuit breakers
↬ Distributed tracing
↬ Metrics design
↬ Log quality
↬ Dependency failure handling
↬ Designing for recovery, not perfection

Execution & Influence
↬ Writing design docs
↬ Getting alignment
↬ Mentoring seniors
↬ Reviewing architecture
↬ Asking better questions
↬ Challenging vague requirements
↬ Explaining tradeoffs simply
↬ Driving cross-team projects
↬ Creating technical standards
↬ Reducing duplicate systems
↬ Unblocking other teams
↬ Making hidden risks visible
↬ Communicating with product
↬ Saying no with reasoning
↬ Turning ambiguity into execution
↬ Making other engineers more effective

The Senior to Staff jump is not just about “I can build complex systems.”

It is:
“I can help the org make better technical decisions, avoid expensive mistakes, and create systems that other engineers can safely build on top of.”

That is the mindset shift imo.

[bodila @51bodila]

Jane Street Quant ~$7M/year showed the fund's code that analyzes ALL MARKET data every millisecond

- the library that made $20.5B/year and nobody talks about

33-min guide on the code a tier-1 fund has been running for ~16 years to stay on top

bookmark & watch - instead of Netflix to learn how to do the same!

[Ronin @DeRonin_]

Andrej Karpathy: "90% of your AI coding bill is paying for context you didn't need to send"

Here are 10 things senior AI engineers stopped wasting tokens on:

1. Auto-context loading 50 files for a 30-line fix: $1.20/turn for tokens you'll never read. 80% input waste, every session

2. Running Opus on lint, format, and rename tasks: $0.60 for what Haiku nails at $0.02. 30x overpay on the cleanup tier

3. Tool call loops that re-send the full repo on every retry: 5x context cost per agentic flow. fixing these alone cuts 30-50% of bills

4. Sonnet as the default model: Kimi 2.6 matches its quality on most coding tasks at 1/6 the cost. defaulting to Sonnet in 2026 is leaving 60-70% on the table

5. Streaming responses on stable-prefix workflows: kills your prompt cache. you pay 10x for tokens that should have cost cents

6. "Just in case" file includes: 80,000-token prompts that should be 3,000. context bloat is the silent budget killer

7. Per-session knowledge rebuilding: 10 min writing a SKILL.md once vs paying agents to re-figure out your environment every run. $4 vs $0.30 per execution

8. Single-model setups: premium tier on every task is the most expensive mistake in AI coding right now

9. Asking 10 small questions one at a time: 10 separate input prefix charges vs one batched call. 70-90% savings on routine workflows

10. Buying Claude Pro + ChatGPT Plus + Cursor Pro: you seriously use one. the other two are habit, not utility

what actually compounds instead:

- context discipline (grep before fetching, always)
- prompt caching on every stable prefix
- multi-model routing (Kimi 2.6 default, Opus for the 10%)
- graduated skills via SKILL.md files
- profiling tool calls before optimizing prompts
- the routing mindset (right model for right task)

in 12 months, the gap between developers shipping on $200/month and $4,000/month budgets won't be skill

it'll be how well they route

study this.

[Khairallah AL-Awady @eng_khairallah1]

🚨 Anthropic pays $750K a year to understand how AI actually works

A Stanford lecture on Agentic AI that teaches you more about how AI automation actually works than 6 months of copying Make and n8n tutorials.

watch the lecture. bookmark it.

Tool calling. Multi-step workflows. Planning. Reflection.

The foundations behind every automation system that actually works.

Most people learn this by copying tutorials blindly.

Stanford teaches you WHY agents work the way they do.

Then read the guide below.

[Math Cafe @Riazi_Cafe_en]

Martin Kleppmann's "Distributed Systems"

Playlist: https://t.co/lZVzM9gB74

Lecture Notes: https://t.co/K30w5IHBrS