Gilberto O Kaestner

Engenheiro Florestal

[Sandra @LadySandraSaray]

Desta metade que é deficiente mental, boa parte está dando aula para a criançada e para os universitários.

[SONIA @S0N_IA]

🚨 ENTIENDES LO QUE ACABA DE PASAR??

Jensen Huang lleva años sin postear en x. hoy rompió el silencio, y no fue para hablar de gpus.

el mensaje decía que la habilidad de ingeniería más valiosa de 2026 no se enseña en ninguna universidad. ni en un bootcamp. ni con un título. según él, el “harness engineering” básicamente, saber diseñar los sistemas que sostienen a un agente de ia cuando las cosas se rompen, es la nueva competencia que separa a quien construye de verdad de quien solo sabe programar.

hace unas semanas ya había soltado otra frase que se quedó dando vueltas: cada ingeniero va a tener y gestionar cientos de agentes. no uno. no un asistente. cientos.

la parte que nadie está mirando: si esto es cierto, el cuello de botella ya no es escribir código. es coordinar sistemas que fallan solos, que se desalinean solos, que necesitan arquitectura de memoria y supervisión constante. eso no es un curso de fin de semana. es una disciplina que todavía se está inventando en tiempo real, y la mayoría de la industria ni siquiera tiene el vocabulario para nombrarla todavía.

guárdalo. dentro de un año esto se va a leer distinto.

[Boris Cherny @bcherny]

Opus 5 is a great model for coding, data analysis, design, biology, knowledge work.

More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully.

And when layering defenses -- strong model alignment, combined with prompt injection probes, combined with Auto Mode in Claude Code -- the success rate for prompt injection attacks drops to ~0. This is new and exciting! More about this soon.

https://t.co/Tc7z2FqJhQ

[Gilberto O Kaestner @Gilbertokaestn]

@botaplayer @Liberfach0 Vai junto para o lixo

[Gilberto O Kaestner @Gilbertokaestn]

@JoaquinTeixeira Vergonha desses dois policiais.

[Punta @PuntaLeyend]

Llamemos a esto EL EMPUJÓN DE DIOS.

[Chris Epp @Chrisskrypto]

An alle Mechaniker, besonders Kfz-Mechatroniker: Sucht euch langsam einen Plan B. Während Deutschland über Gaspreise diskutiert, arbeiten in China bereits humanoide Roboter in Werkstätten. Glaubt ihr wirklich, euer Job ist noch lange sicher?

Ihr seid in 2 Jahren Arbeitslos!

[Gilberto O Kaestner @Gilbertokaestn]

@astropol0 Yes and kimi k3 tuned 3.1

[Gilberto O Kaestner @Gilbertokaestn]

@joaohazim @Seergiot3ck Uma tropa de jumentos.

[عشيرج @asheirgk61]

@said_modric10 اوتمندي لاعب قذر ونجس ومنتخب
فاشل وصل النهائي بجهود الحكام
والدليل مستوى فاشل ولاعبين
فاشلين يلعبون بالخشونة المفرطة
ونرفزة الخصم وهذه الطريقة
يستعملها الفاشلين المفروض
منتخب الراس الاخضر اهو مكان
الارجنتين عمومآ نهاية مذلة نتيجة
ومستوى واخلاقيآ

[Rick Jones @Bazooker]

@_matheusfla

[Gilberto O Kaestner @Gilbertokaestn]

@wofaase_ muito mimado o ultimo cliente. Não consegue viver no Brasil.

[Gilberto O Kaestner @Gilbertokaestn]

@Clip_Station_ Uma piranha que não sabe seu lugar.

[Gilberto O Kaestner @Gilbertokaestn]

@PsyGuy007 A cara de vagabundos

[Monica Laredo @MonicaLaredo2]

O prefeito de Nova York, Mandani, ficou furioso com Israel por eliminar Ahmed Wishah, um “jornalista” da Al Jazeera, ontem.

Ele parece um “jornalista” inocente para você?

[Meta Alchemist @meta_alchemist]

Got your hands on Claude Fable 5?

The first thing you should do is to upgrade your main projects with it, so it drastically impoves everything you've been working on.

Run this Audit & Project Improvement Prompt on each repo that's important to you (simply copy-paste it):

Repo Audit & Improvement Plan:
Prompt made by Claude Fable 5

You are a world-class principal-level software engineer and technical auditor. Your job is to deeply analyze this repository, produce an honest audit, and deliver a prioritized, actionable improvement plan. Work in the four phases below, in order. Do not skip ahead.

Ground every claim in actual files: cite file paths and line numbers. If you can't verify something, say so explicitly rather than guessing.

Phase 1 / Discovery & Mapping (read before judging)
Explore the repository systematically before forming any opinions:

Map the directory structure and identify the project type, language(s), frameworks, and runtime targets.
Identify entry points, core modules, and the main data/control flow through the system.

Read the package manifest(s), lockfiles, build config, CI config, environment/config files, and any docs (README, CONTRIBUTING, ADRs).

Determine what the project is for: its purpose, intended users, and apparent maturity (prototype, internal tool, production service, library).

Note conventions already in use (naming, module boundaries, error handling patterns, test style) so recommendations fit the existing culture rather than fighting it.

Output for this phase: a concise "Repo Map" purpose, stack, architecture sketch, key directories with one-line descriptions, and anything that surprised you.

Phase 2 / Audit (evidence-based, severity-rated)

Audit each dimension below.

For every finding, record: (a) what you found, (b) where (file:line), (c) why it matters (concrete consequence, not vague principle), (d) severity:

Critical / High / Medium / Low.

• Architecture & design: module boundaries, coupling/cohesion, circular dependencies, leaky abstractions, god objects/files, layering violations, scalability bottlenecks.

• Code quality: duplication, dead code, complexity hotspots (longest/most-branched functions), inconsistent patterns, error handling gaps (swallowed exceptions, missing edge cases), type safety holes.

• Security: hardcoded secrets or credentials, injection risks, unsafe deserialization, missing input validation, auth/authz weaknesses, outdated dependencies with known CVEs, overly permissive configs.

• Testing: coverage gaps (especially around core business logic), test quality (do tests assert behavior or just execution?), missing test types (unit/integration/e2e), flaky patterns, untestable code.

• Performance: N+1 queries, unnecessary allocations or copies, blocking calls in async paths, missing caching/indexing, unbounded growth (memory, files, queues).

• Dependencies: outdated, unmaintained, duplicated, or unnecessarily heavy packages; license risks; lockfile hygiene.

• DevEx & operations: build/setup friction, CI/CD gaps, missing linting/formatting enforcement, logging/observability quality, error reporting, deployment story.

• Documentation: README accuracy, onboarding path, undocumented critical behavior, stale docs that contradict code.

Rules for this phase:

Prefer 15 high-confidence findings over 50 speculative ones.

Distinguish facts ("this function has no error handling: src/api/client.ts:142") from judgments ("this module's responsibilities feel unclear") and label which is which.

Also list what the repo does well: strengths matter for deciding what to preserve.

Output for this phase: an "Audit Report": findings grouped by dimension, sorted by severity, plus a Strengths section.

Don't forget to mention all the ugly parts that need utmost priority.

Phase 3 / Improvement Strategy

Synthesize the audit into a strategy:

Identify the 3–5 themes that explain most of the findings (e.g., "no enforced boundaries between layers," "error handling is ad hoc").

For each theme, propose a target state and the principle behind it.

State explicit trade-offs: what you're recommending NOT to fix and why (effort vs. payoff, risk, project maturity).

Define what "done" looks like — measurable signals (e.g., "CI fails on lint errors," "core module test coverage ≥ 80%," "zero Critical findings").

Phase 4 / Detailed Task Plan
Convert the strategy into an execution plan:

Break work into discrete tasks. Each task must include: Title and one-paragraph description
Files/areas affected

Acceptance criteria (how we verify it's done)
Effort estimate (S = <2h, M = half-day, L = 1–2 days, XL = needs breakdown)

Risk of the change itself (could it break things?)
Dependencies on other tasks

Order tasks into milestones:

Milestone 0
Safety net: anything needed before refactoring safely (tests around critical paths, CI gates, backups).

Milestone 1
Critical fixes: security and correctness issues.

Milestone 2
High-leverage improvements: changes that make all future work easier.

Milestone 3
Quality & polish: remaining medium/low items worth doing.

Flag quick wins (high impact, S effort) separately so they can be done immediately.

For the top 3 tasks, include a brief implementation sketch (approach, key steps, gotchas).

Final Deliverable Format
• Produce a single document with these sections:
• Executive Summary (≤10 sentences: overall health grade A–F with justification, top 3 risks, top 3 opportunities)
• Repo Map
• Audit Report
• Improvement Strategy
• Task Plan (milestones + task table + quick wins)
• Open Questions: anything you need from a human to decide (product intent, deprecation candidates, performance targets)

Constraints
Do NOT modify any code during this audit. Analysis only.

Do not pad the report. If a dimension is healthy, say so in one sentence and move on.

Calibrate to the project's maturity. Don't recommend enterprise-grade infrastructure for a weekend prototype unless the owner's goals demand it.

Analyze the project's needs and provide recommendations in the most effective ways.

If the repo is large, prioritize depth in the core 20% of code that does 80% of the work, and note which areas received lighter review.

[Jota. @jota_snchez]

Dos ingenieros de Anthropic dedicaron 24 minutos explicando funciones de Claude Code que casi nadie conoce.

La mayoría va a ignorarlo.

10 consejos para dominar Claude

1) Sé muy claro y consiso

[Gilberto O Kaestner @Gilbertokaestn]

@Capitana_espana Chega sem conversa ja no chute

[Gilberto O Kaestner @Gilbertokaestn]

@isaacrrr7 Elegante e feminina