Naoki

[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.

[Naoki @Naoki649969]

@twoclipping Prompts

[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.

[Theo - t3.gg @theo]

It’s getting worse guys