Naoki

[Suraj Sharma @suraj_sharma14]

Want to be a Backend Architect in July 2026.

Please learn.

1. Agentic System Design
Service decomposition for agents, bounded contexts for workflows, resilience patterns for non-deterministic systems.

2. Distributed AI Infrastructure
Container orchestration for inference, Kubernetes for agents, multi-model routing, edge deployment strategies.

3. Hybrid Data Architecture
Vector databases, traditional SQL/NoSQL, embedding pipelines, data versioning, point-in-time correctness for ML.

4. Agent Interface Design
MCP protocol, structured tool calling, API gateways for agents, asynchronous command queues, webhook orchestration.

5. Event-Driven Agent Workflows
Kafka for agent triggers, pub/sub for multi-agent communication, saga patterns for long-running agent transactions.

6. AI Observability and Tracing
Distributed tracing for agent steps, cost attribution per request, latency monitoring, drift detection, eval pipelines.

7. AI Security and Guardrails
Prompt injection defense, PII redaction pipelines, zero trust for agent tool access, audit trails for autonomous actions.

8. Infrastructure as Code for AI
Terraform for vector infra, Helm charts for model serving, configuration management for prompt versions and model weights.

9. Scaling and Cost Optimization
Horizontal scaling for stateless agents, KV cache optimization, token budgeting, model routing by cost and latency.

10. Reliability and Recovery
Circuit breakers for LLM failures, retry logic with exponential backoff, fallback models, graceful degradation patterns.

Most people stay stuck watching tutorials.

Builders get hired.

[Machina @EXM7777]

ElevenLabs founders must be SHAKING right now...

for years they owned TTS because nothing open-source sounded human

that’s over... Fish Audio just launched S2.1 Pro and they’re one of the few voice AI companies that also has open-weight models

> clone any voice from a 15 second clip
> type [whispers] or [laughing nervously] into the script and it obeys
> switch languages mid conversation without switching models

the model you used to rent a subscription for is now has a public download model

tinker with the weights on your own gpu or use the api

[diva @divaagurlxw]

As an AI Engineer. Please learn

>Harness engineering, not just prompt engineering

>Context engineering, not just long prompts

>Prompt caching vs. semantic caching tradeoffs

>KV cache management, eviction, reuse, and memory pressure at scale

>Prefill vs. decode latency and why they optimize differently

>Continuous batching, paged attention, and throughput optimization

>Speculative decoding vs. quantization vs. distillation tradeoffs

>INT8, INT4, FP8, AWQ, GPTQ, and when quantization hurts quality

>Structured output failures, schema validation, repair loops, and fallback chains

>Function calling reliability, tool contracts, argument validation, and idempotency

>Agent guardrails, loop budgets, tool budgets, and termination conditions

>Model routing, graceful fallback logic, and degraded-mode UX

>RAG architecture: chunking, embeddings, hybrid search, reranking, and freshness

>Retrieval evals: recall, precision, grounding, attribution, and citation quality

>Evals: golden sets, regression tests, adversarial tests, LLM-as-judge, and human evals

>LLM observability as a first-class discipline: traces, spans, tokens, latency, errors, and drift

>Cost attribution per feature, workflow, tenant, and user journey not just per model

>Safety engineering: prompt injection defense, data leakage prevention, and permission boundaries

>Multi-tenant isolation, cache safety, and cross-user context contamination prevention

>Fine-tuning vs. in-context learning vs. RAG vs. distillation and when each is the wrong tool

>Latency, quality, cost, and reliability tradeoffs across the full inference stack

>Production failure modes: hallucinated tool calls, malformed JSON, stale retrieval, runaway agents, and silent eval regressions

[Uncle Bob Martin @unclebobmartin]

I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.

[vasyl @waitwuut]

кубоподібні стелі airflow кор

[Aaron Epstein @aaron_epstein]

Designing your dream home just got even faster

[Viktor Oddy @viktoroddy]

The New GPT 5.6 Sol is insane.

❤️‍🔥Just recorded a 21-min Full Tutorial on How To Build Premium, Cinematic Websites with GPT 5.6 Sol!

[Rubén, vuestro amigo @PizzaL0sViernes]

El 51% del Parlamento Europeo acaba de votar a FAVOR del #ChatControl

Os dejo un tutorial para aprender a enviar mensajes encriptados usando https://t.co/De1008bcu4 que contiene GnuPG (la herramienta en sí) + Kleopatra (interfaz de usuario que simplifica las cosas)

[OpenAI @OpenAI]

Introducing GPT-Live, a new generation of voice models for natural human-AI interaction.

Rolling out in ChatGPT starting today.

You’ll want to turn the sound on for this one.

[Md Ismail Šojal 🕷️ @0x0SojalSec]

A 27B Uncensored model that built for specifically for offensive security tooling (need 12 GB)

- Fine-tuned on real bug bounty reports & CVEs
- Generates complete, ready-to-run Nuclei templates, Full CVE PoC script, Webshell upload bypass, and exploits, code reviews
- Zero refusals. Full artifacts every time.

trained with 2,541 of real bug bounty & offensive security reports.

Q6_K quant (21GB) for maximum quality on server-grade GPUs.

[Tom Dörr @tom_doerr]

Fitness dataset with animation GIFs and bilingual instructions

https://t.co/JsCroM0Lye

[Keilthar @Keilthar]

L'ingénieur en moi trouve ça génial.
L'informaticien en moi trouve ça grave.

[Enrique @enriqdev]

Google fue muy listo; usan los acelerómetros de miles de teléfonos Android cómo una red global de sismos, toda esa data se envía y Google logró una forma de detectar esas ondas a tiempo y enviar las alertas.

[Naoki @Naoki649969]

@MaryMuffin__ @SIgneS89694743 @Backslash4 @elEconomistaes

[Naoki @Naoki649969]

@MaryMuffin__ @SIgneS89694743 @Backslash4 @elEconomistaes Marrón

[Naoki @Naoki649969]

@peremayol @lalgorisme Correcte

[santi @santtiagom_]

se sumó mucha gente a partir de este tweet 🙏

les dejo mis posts más importantes para empezar a aprender de IA desde cero:

1) Qué es un agente
https://t.co/pR2uGS5Wn2

2) Empezar con Claude Code
https://t.co/1yM8CqZB27

3) Arquitectura de Claude Code
https://t.co/aZQ3ckV99V

4) Anatomía de un Agente
https://t.co/zuh0fACMhm

5) Claude: Prompt, MCP, Skill & Subagent
https://t.co/zhqeIcrVS3

6) Harness Engineering
https://t.co/q09Tqldlia

7) Agente = modelo + harness
https://t.co/afElqdz0sj

8) Guía de Skills (artículo)
https://t.co/JlqTvbTcsi

9) Prompting Engineer con Claude
https://t.co/MCaWjpLJFq

10) Hermes Agent
https://t.co/x8p49RvH2R

espero que les sirva de guía para arrancar 🫡

[Naoki @Naoki649969]

@Deploy_U @OlgaPereda

[Naoki @Naoki649969]

@JosAntonio41740 @Macarena_Olona No ets conscient de l’ho català que era Gaudí

[modyfikatorcasper @Modyfikator89]

HISTORIC BREAKTHROUGH: UNPATCHABLE CALIBRATION
We cracked it! Massive thanks to Lewy20041 & @driftguardapp for this historic hardware discovery. We have unlocked ultimate manual & automatic joystick Calibration for any Xbox Contoller 🎮
It is UNPATCHABLE and PERMANENT written directly into the controller's memory forever. It cannot block this.