Essays on agents, applied AI and governance.https://elzobrito.github.io/https://elzobrito.github.io/en/blog/a-markdown-folder-is-still-not-a-note-system/https://elzobrito.github.io/en/blog/a-markdown-folder-is-still-not-a-note-system/A folder full of .md files is still only a file collection: wiki links do not resolve and there is no reverse index, it is not a note system until links exist in the system.Sun, 20 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/restricting-the-frontier-requires-proving-narrower-defenses-failed/https://elzobrito.github.io/en/blog/restricting-the-frontier-requires-proving-narrower-defenses-failed/Restricting or deliberately slowing frontier AI capability in the name of catastrophic risk must carry the burden of justification, including the opportunity cost of delayed defenses and medical or scientific progress. That logic applies to risk governance in general, not only bioweapon narratives.Tue, 15 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-prompt-describes-the-cycle-esaa-institutes-it/https://elzobrito.github.io/en/blog/the-prompt-describes-the-cycle-esaa-institutes-it/Codex-on-GPT-6 agent instructions already narrate claim/complete, evidence rules, and completion audits in natural language. ESAA formalizes the same lifecycle outside the model: event sourcing and a deterministic orchestrator.Thu, 10 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/formalization-closes-the-statement-not-the-dispute/https://elzobrito.github.io/en/blog/formalization-closes-the-statement-not-the-dispute/OpenAI published a Lean proof of forced blowup for Navier–Stokes, matching Clay’s (C)/(D). That closes a formalizable mathematical statement; it does not by itself settle priority, what the community calls “the” problem, or prize acceptance.Wed, 09 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-got-more-aligned-and-harder-to-audit/https://elzobrito.github.io/en/blog/ai-got-more-aligned-and-harder-to-audit/GPT-6 Astra produced fewer severe violations in one deployment simulation while making written reasoning less legible to monitors. Safety now requires the full trajectory.Fri, 04 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/auditable-control-of-action-trajectories-became-the-scarce-resource/https://elzobrito.github.io/en/blog/auditable-control-of-action-trajectories-became-the-scarce-resource/GPT-6 Astra drives the computer on a minutes scale and clears the Critical cyber bar. The bottleneck shifts from readable CoT to tools, duration, and access gates.Fri, 04 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/before-delegation-intention-must-become-an-artifact/https://elzobrito.github.io/en/blog/before-delegation-intention-must-become-an-artifact/Anthropic’s AI-native SDLC playbook puts intent.md at the center: why, outcome, and constraints leave the chat and enter version control before an agent writes code.Fri, 04 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/hypotheses-got-cheap-the-lab-is-still-scarce/https://elzobrito.github.io/en/blog/hypotheses-got-cheap-the-lab-is-still-scarce/DeepMind’s Co-Scientist designs experiments while humans execute in the lab. The real advance is not full autonomy: it is the bottleneck moving from hypothesis generation to experimental capacity and verification.Fri, 04 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-teammate-stopped-being-a-session/https://elzobrito.github.io/en/blog/the-teammate-stopped-being-a-session/Grok Bot for Enterprise treats each Bot as a worker with its own cloud computer, a routine learned once, and Bot-to-Bot context handoff—not a chat that vanishes when the tab closes.Fri, 04 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/a-complex-harness-is-the-exam-rankings-do-not-run/https://elzobrito.github.io/en/blog/a-complex-harness-is-the-exam-rankings-do-not-run/Gemini 3.8 Flash joined the small group of models that can do daily work: it survived a complex harness, with a large context, without losing the thread. That is the same threshold Grok 4.5 crossed when it became usable for programming.Wed, 02 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/intelligence-now-depends-on-the-badge/https://elzobrito.github.io/en/blog/intelligence-now-depends-on-the-badge/Fable 5.1 and Mythos 5.1 share a model but change access, safeguards, and retention. The release shows why capability alone no longer describes an AI product.Wed, 02 Sep 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/multimodal-latency-starts-before-the-gpu/https://elzobrito.github.io/en/blog/multimodal-latency-starts-before-the-gpu/A vLLM change shows how images, audio, and video can delay a response before inference begins, and why useful concurrency must preserve order, failures, and equivalence.Mon, 31 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-gpu-stack-now-comes-with-an-operations-agent/https://elzobrito.github.io/en/blog/the-gpu-stack-now-comes-with-an-operations-agent/ROCm 10 signals a shift in AI infrastructure: installation, diagnosis, and tuning are becoming executable, testable workflows rather than documentation alone.Fri, 28 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/long-context-became-an-architecture-problem/https://elzobrito.github.io/en/blog/long-context-became-an-architecture-problem/Qwen3.8-Flash-Next illustrates an important shift: extending context now means combining specialized paths for memory, selection, and scale rather than relying on one attention mechanism.Wed, 26 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-model-is-a-brain-in-a-jar/https://elzobrito.github.io/en/blog/the-model-is-a-brain-in-a-jar/Two products can share a model and still feel like different systems. The difference is usually the harness: tools, memory, and the loop that turns reasoning into action.Tue, 25 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/context-needs-a-type-system-too/https://elzobrito.github.io/en/blog/context-needs-a-type-system-too/New Codex changes show why truncating, compacting, and splitting a conversation must preserve not only content but also the source and role of each part.Mon, 24 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/a-screen-records-steps-not-the-work/https://elzobrito.github.io/en/blog/a-screen-records-steps-not-the-work/A new method turns computer-use traces into auditable models of goals and procedures, showing measurable gains and a serious privacy boundary.Fri, 21 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-agent-learned-to-speak-without-stopping/https://elzobrito.github.io/en/blog/the-agent-learned-to-speak-without-stopping/Asynchronous updates and thread-scoped approvals show what changes when an agent must inform, continue, and keep contexts separate.Wed, 19 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/a-cache-must-know-when-data-is-still-alive/https://elzobrito.github.io/en/blog/a-cache-must-know-when-data-is-still-alive/Three vLLM fixes show how preemption, overlapping copies, and late notifications can turn AI caching into incorrect state.Mon, 17 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/autonomy-starts-before-the-first-line-of-code/https://elzobrito.github.io/en/blog/autonomy-starts-before-the-first-line-of-code/New Codex diagnostics and boundaries show why a coding agent must understand the machine it runs on, not only the repository.Sun, 16 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/claudes-invisible-mark-is-more-fragile-than-it-looks/https://elzobrito.github.io/en/blog/claudes-invisible-mark-is-more-fragile-than-it-looks/Anthropic now marks text and files to comply with the EU AI Act. Here is what is confirmed, what remains secret, and why rewriting can erase the signal.Sun, 16 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/reasoning-got-a-control-knob/https://elzobrito.github.io/en/blog/reasoning-got-a-control-knob/Qwen3.8-27B, Ollama, and llama.cpp show that choosing how much a model reasons requires a contract across weights, templates, and runtimes.Fri, 14 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-changed-without-changing-a-single-weight/https://elzobrito.github.io/en/blog/ai-changed-without-changing-a-single-weight/Fixes in Transformers and vLLM, plus a new Ollama default, show how configuration and sampling can alter model behavior while weights remain untouched.Thu, 13 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/compatibility-does-not-inherit-security/https://elzobrito.github.io/en/blog/compatibility-does-not-inherit-security/Changes in vLLM, Codex, and llama.cpp show why endpoints, delegated agents, and model files need explicit trust boundaries.Wed, 12 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-benchmark-now-comes-with-assembly-instructions/https://elzobrito.github.io/en/blog/the-benchmark-now-comes-with-assembly-instructions/Nemotron 3.5 Lightning arrives with open weights and reproducible evaluation recipes, revealing how much a score depends on both the model and the environment that produced it.Tue, 11 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-agent-fits-in-24-gb-trust-does-not/https://elzobrito.github.io/en/blog/the-agent-fits-in-24-gb-trust-does-not/Muse Glimmer 30B brings vision, tool use, and speculative inference to consumer hardware, while its own evaluations show why local execution still needs supervision.Mon, 10 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-agent-got-an-identity-that-expires/https://elzobrito.github.io/en/blog/the-agent-got-an-identity-that-expires/Two Codex changes turn workload identity into short-lived access and stop launch context from flowing into child processes.Sun, 09 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/a-folder-is-not-a-permission/https://elzobrito.github.io/en/blog/a-folder-is-not-a-permission/llama.cpp is beginning to separate the file interface from the environment where tools actually run, giving local agents more verifiable boundaries.Sat, 08 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/scarce-memory-becomes-inference-policy/https://elzobrito.github.io/en/blog/scarce-memory-becomes-inference-policy/vLLM and llama.cpp now treat cache, disk, and model eviction as explicit capacity decisions rather than invisible server details.Fri, 07 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-inference-stack-learns-to-work-in-pieces/https://elzobrito.github.io/en/blog/the-inference-stack-learns-to-work-in-pieces/Two vLLM changes separate request preparation, model execution, and GPU dependency, making infrastructure easier to test without hiding its limits.Thu, 06 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/metrics-make-speculative-decoding-auditable/https://elzobrito.github.io/en/blog/metrics-make-speculative-decoding-auditable/llama.cpp now exposes speculative-decoding counters through /metrics, bringing an inference optimization closer to the observability needed to decide whether it pays off.Wed, 05 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/local-voice-gains-a-new-model-but-loses-compatibility/https://elzobrito.github.io/en/blog/local-voice-gains-a-new-model-but-loses-compatibility/llama.cpp's Qwen3-TTS support expands local speech generation while showing why a command-line interface is also an AI integration contract.Tue, 04 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/agent-engineering-is-not-vibe-coding-with-more-autonomy/https://elzobrito.github.io/en/blog/agent-engineering-is-not-vibe-coding-with-more-autonomy/The distinction between programming a flow, delegating to an agent, and building a reliable agent system lies in boundaries, evidence, and accountability.Mon, 03 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-transparency-became-an-interface-requirement/https://elzobrito.github.io/en/blog/ai-transparency-became-an-interface-requirement/GitHub's retirement of Copilot Billing Preview shows that measuring AI use, cost, and accountability no longer fits in a separate screen.Mon, 03 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/local-ai-must-treat-speed-and-protocol-as-one-problem/https://elzobrito.github.io/en/blog/local-ai-must-treat-speed-and-protocol-as-one-problem/llama.cpp's August 2 updates connect speculative decoding, tool calls, and telemetry: useful performance depends on contracts that survive execution.Sun, 02 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-cache-that-speeds-up-ai-must-also-separate-users/https://elzobrito.github.io/en/blog/the-cache-that-speeds-up-ai-must-also-separate-users/vLLM's new cache_salt support for the Anthropic API shows why prefix reuse in shared environments needs an explicit boundary between users.Sat, 01 Aug 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-needs-to-show-its-work/https://elzobrito.github.io/en/blog/ai-needs-to-show-its-work/OSReward and AskChem point to the same shift: dependable agents must preserve the path of an action and the provenance of every claim.Fri, 31 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-agent-ran-the-experiment-but-did-not-do-the-research/https://elzobrito.github.io/en/blog/the-agent-ran-the-experiment-but-did-not-do-the-research/A new evaluation gave frontier agents six days, a budget, and full infrastructure. They completed the engineering but lacked the judgment that turns work into research.Thu, 30 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/code-security-leaves-the-dashboard-and-enters-the-terminal/https://elzobrito.github.io/en/blog/code-security-leaves-the-dashboard-and-enters-the-terminal/OpenAI has opened the Codex Security CLI and TypeScript SDK, bringing threat models, validation, scan history, and change review to local repositories and CI.Wed, 29 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/software-security-moved-earlier/https://elzobrito.github.io/en/blog/software-security-moved-earlier/npm, GitHub Actions, Dependabot, and CodeQL are shifting controls ahead of package availability, workflow execution, and malicious-code propagation.Wed, 29 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/agents-write-the-code-not-the-proof/https://elzobrito.github.io/en/blog/agents-write-the-code-not-the-proof/Eight scientific-computing projects show that agents can already rewrite and accelerate complex software. Validation, interpretation, and stewardship are now the bottleneck.Tue, 28 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/two-quiet-shortcuts-for-local-ai/https://elzobrito.github.io/en/blog/two-quiet-shortcuts-for-local-ai/llama.cpp added Eagle3-v3 support for GPT-OSS and a Hadamard kernel for Apple Metal, showing two distinct ways inference can avoid wasted work.Tue, 28 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/before-acting-an-agent-must-prove-it-is-ready/https://elzobrito.github.io/en/blog/before-acting-an-agent-must-prove-it-is-ready/NemoClaw and MinerU reveal a quiet shift in AI infrastructure: readiness, uncertainty, and shutdown need verifiable contracts.Mon, 27 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/down-youtube-local-youtube-transcription-with-whisper-and-rag-memory/https://elzobrito.github.io/en/blog/down-youtube-local-youtube-transcription-with-whisper-and-rag-memory/Open-source desktop app to download, transcribe, and organize YouTube or local media: whisper.cpp, playlists, long-audio chunking, best-effort media quality, and local RAG over your transcript library.Mon, 27 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-infrastructure-learns-to-say-no/https://elzobrito.github.io/en/blog/ai-infrastructure-learns-to-say-no/vLLM 0.26.0 shows that serving models safely requires bounding work, memory, and inputs, not merely accelerating tokens.Sun, 26 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/elon-musk-economist-2026-abundance-ai-and-the-price-of-control/https://elzobrito.github.io/en/blog/elon-musk-economist-2026-abundance-ai-and-the-price-of-control/A dense reading of the July 2026 interview: superintelligence timelines, digital and physical AI, money, existential risk, China, labor, and the tension between civilizational utopia and political tribalism.Sun, 26 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-the-computer-disappears-gates-ai-and-the-interface-of-intent/https://elzobrito.github.io/en/blog/when-the-computer-disappears-gates-ai-and-the-interface-of-intent/The 1990s claim that the computer would stop being an object and become infrastructure is back with force: AI does not erase silicon; it erases the conscious act of computing.Sun, 26 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/intelligence-is-now-a-budget-variable/https://elzobrito.github.io/en/blog/intelligence-is-now-a-budget-variable/Claude Opus 5 brings frontier-level capability closer to everyday use and exposes a choice that was already there: how much reasoning, time, and money each task deserves.Sat, 25 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/open-weights-why-ai-leadership-does-not-fit-in-a-single-model/https://elzobrito.github.io/en/blog/open-weights-why-ai-leadership-does-not-fit-in-a-single-model/A coalition of big tech and the open-weight ecosystem argues that American AI leadership depends on diffusion, competition, and local control, not on one frontier model.Sat, 25 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/agents-got-brakes-not-walls/https://elzobrito.github.io/en/blog/agents-got-brakes-not-walls/New GitHub controls make agent actions reviewable and explainable while MCP drops sessions to scale. The gap between oversight and security is now easier to see.Fri, 24 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/coding-ai-enters-its-accountability-phase/https://elzobrito.github.io/en/blog/coding-ai-enters-its-accountability-phase/GitHub's new Copilot impact dashboard moves beyond usage counts toward cohorts, delivery, and velocity, while exposing why contribution still needs careful context.Thu, 23 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/control-is-also-part-of-the-ai-product/https://elzobrito.github.io/en/blog/control-is-also-part-of-the-ai-product/OpenAI Presence packages policies, evaluations, and escalation for agents, while a security incident shows the cost of treating containment as infrastructure detail.Wed, 22 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/rag-sqlite-local-rag-in-one-python-script-plus-sqlite-built-for-agents/https://elzobrito.github.io/en/blog/rag-sqlite-local-rag-in-one-python-script-plus-sqlite-built-for-agents/A Python CLI over SQLite that chunks text, embeds it, and returns stable JSON for LLM tool-calling, without Flask, Postgres, or a worker.Wed, 22 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-steps-off-the-screen-and-into-the-physical-world/https://elzobrito.github.io/en/blog/ai-steps-off-the-screen-and-into-the-physical-world/Cosmos 3 Edge brings world models closer to local robots and cameras, while creative tools begin exposing standardized interfaces for agents.Tue, 21 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-ai-race-moves-down-the-stack/https://elzobrito.github.io/en/blog/the-ai-race-moves-down-the-stack/Alibaba's new architecture shows why agents depend on observability, routing, and hardware software as much as on the model.Mon, 20 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-real-price-of-a-million-tokens/https://elzobrito.github.io/en/blog/the-real-price-of-a-million-tokens/Kimi K3's pricing shows why long context depends less on the advertised limit than on caching, output, and application design.Sun, 19 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-ai-stops-guessing-the-docs/https://elzobrito.github.io/en/blog/when-ai-stops-guessing-the-docs/Grounded answers, configurable reviews, and repository metrics point toward more verifiable AI development tools.Sat, 18 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-agents-attack-and-notebooks-execute/https://elzobrito.github.io/en/blog/when-agents-attack-and-notebooks-execute/An agent-driven intrusion and code execution in research notebooks show why context, action, and isolation now belong in the same design conversation.Fri, 17 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-defense-also-learns-to-attack/https://elzobrito.github.io/en/blog/when-defense-also-learns-to-attack/GPT-Red turns adversarial testing into continuous training, while new GitHub controls show how security signals can reach real development workflows.Thu, 16 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-security-moves-before-the-merge/https://elzobrito.github.io/en/blog/ai-security-moves-before-the-merge/New GitHub reviews bring contextual analysis into active coding and pull requests, expanding coverage without replacing deterministic checks.Wed, 15 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/slowing-ai-is-an-engineering-problem/https://elzobrito.github.io/en/blog/slowing-ai-is-an-engineering-problem/Putting brakes on the race for more capable systems means turning caution into verifiable mechanisms, economic incentives, and institutional accountability.Tue, 14 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-ai-needs-a-checker/https://elzobrito.github.io/en/blog/when-ai-needs-a-checker/New work on formal proofs, backend generation, and document understanding shows why useful AI must verify results, not merely produce them.Tue, 14 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/the-fragile-edges-of-agents-reviews-reasoning-and-images/https://elzobrito.github.io/en/blog/the-fragile-edges-of-agents-reviews-reasoning-and-images/Recent Codex and llama.cpp fixes show why reliable agents depend on stable reviewers, multimodal adapters, and well-defined message boundaries.Mon, 13 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/agents-become-platforms-skills-plugins-and-local-control/https://elzobrito.github.io/en/blog/agents-become-platforms-skills-plugins-and-local-control/Projects gaining attention across the open ecosystem point to an important shift: AI agents are moving beyond isolated apps toward portable extensions, local tools, and reusable contracts.Sun, 12 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-agents-between-autonomy-and-governance/https://elzobrito.github.io/en/blog/ai-agents-between-autonomy-and-governance/The new frontier for AI agents is not only better answers, but closed work loops: observing data, proposing hypotheses, taking action, and returning evidence for human review.Sun, 12 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/j-space-discovery-or-constructed-workbench/https://elzobrito.github.io/en/blog/j-space-discovery-or-constructed-workbench/A critical reading of the study on Claude's alleged global workspace: what already existed in the model, what the J-lens constructed, and what the experiments actually support.Sun, 12 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/why-agents-need-governance/https://elzobrito.github.io/en/blog/why-agents-need-governance/Useful autonomy requires clear boundaries, verifiable memory and accountability for every effect.Sun, 12 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/event-sourcing-for-agents/https://elzobrito.github.io/en/blog/event-sourcing-for-agents/How immutable events and deterministic projections make AI workflows auditable and reproducible.Fri, 10 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/applied-ai-with-evidence/https://elzobrito.github.io/en/blog/applied-ai-with-evidence/A practical approach to move beyond the demo and build systems teams can evaluate.Wed, 08 Jul 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/how-grok-build-helped-me-use-linux-for-real/https://elzobrito.github.io/en/blog/how-grok-build-helped-me-use-linux-for-real/A curated English edition about using an agent to turn Linux from a technical alternative into a practical daily system.Sat, 27 Jun 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/stop-asking-ai-to-find-bugs-meet-esaa-security/https://elzobrito.github.io/en/blog/stop-asking-ai-to-find-bugs-meet-esaa-security/A curated English edition introducing ESAA-Security as a governed alternative to vague AI bug hunting.Wed, 24 Jun 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/when-trace-logs-become-constant-ssd-writes/https://elzobrito.github.io/en/blog/when-trace-logs-become-constant-ssd-writes/A curated English edition about noticing operational side effects from verbose tracing and protecting local hardware.Tue, 23 Jun 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/conversation-esaa-shared-memory-between-ai-agents/https://elzobrito.github.io/en/blog/conversation-esaa-shared-memory-between-ai-agents/A curated English edition introducing Conversation ESAA as shared operational memory for agent work.Mon, 22 Jun 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/esaa-three-months-later-what-happened-when-others-started-implementing/https://elzobrito.github.io/en/blog/esaa-three-months-later-what-happened-when-others-started-implementing/A curated English edition about the transition from a personal protocol to implementations by other people.Sat, 13 Jun 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/stop-letting-llms-edit-code-directly-meet-esaa-architecture/https://elzobrito.github.io/en/blog/stop-letting-llms-edit-code-directly-meet-esaa-architecture/A curated English edition explaining ESAA as Event Sourcing for autonomous agents.Sat, 28 Feb 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/autonomous-wave-from-copilot-to-autopilot/https://elzobrito.github.io/en/blog/autonomous-wave-from-copilot-to-autopilot/A concise English edition about AI moving from assistive copilots toward more autonomous workflows.Sun, 15 Feb 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/open-source-leap-kimi-k2-5-and-agent-swarms/https://elzobrito.github.io/en/blog/open-source-leap-kimi-k2-5-and-agent-swarms/A translated editorial note on open-source model progress and multi-agent coordination.Wed, 28 Jan 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/rise-of-ai-agents-from-tools-to-teammates/https://elzobrito.github.io/en/blog/rise-of-ai-agents-from-tools-to-teammates/A migrated English edition on AI agents as collaborators inside work systems.Tue, 27 Jan 2026 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-revolution-from-hollywood-stage-to-cancer-treatment/https://elzobrito.github.io/en/blog/ai-revolution-from-hollywood-stage-to-cancer-treatment/A curated English edition of a broad AI analysis post connecting media, science, and applied research.Thu, 02 Oct 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/openai-trillion-dollar-bet-ai-virus-generation-earth-modeling-training-data/https://elzobrito.github.io/en/blog/openai-trillion-dollar-bet-ai-virus-generation-earth-modeling-training-data/A curated English edition of an AI news analysis post about infrastructure, biology, climate modeling, and training data.Thu, 02 Oct 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/accelerating-ai-from-quantum-atoms-to-social-video-and-work/https://elzobrito.github.io/en/blog/accelerating-ai-from-quantum-atoms-to-social-video-and-work/A curated English edition of an AI radar article about scientific, social, and workplace acceleration.Wed, 01 Oct 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-revolution-sora-2-intelligent-agents-and-workslop/https://elzobrito.github.io/en/blog/ai-revolution-sora-2-intelligent-agents-and-workslop/A curated English edition about AI media generation, agents, and the risk of low-quality automated work.Wed, 01 Oct 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-revolution-from-autonomous-agents-to-strategic-partnerships/https://elzobrito.github.io/en/blog/ai-revolution-from-autonomous-agents-to-strategic-partnerships/An English adaptation of the legacy article on agents, autonomy, and more strategic human-machine collaboration.Fri, 19 Sep 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/cunning-ai-when-models-learn-to-be-too-clever/https://elzobrito.github.io/en/blog/cunning-ai-when-models-learn-to-be-too-clever/An English adaptation on models optimizing around tests, incentives, and human expectations.Fri, 19 Sep 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/building-a-hybrid-excel-chat-with-ollama-and-gpt-4o-mini/https://elzobrito.github.io/en/blog/building-a-hybrid-excel-chat-with-ollama-and-gpt-4o-mini/A migrated implementation note on combining offline and online models for spreadsheet workflows.Fri, 16 May 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/openai-for-countries-a-step-in-the-right-direction/https://elzobrito.github.io/en/blog/openai-for-countries-a-step-in-the-right-direction/A translated editorial note on national AI infrastructure and public-sector capability.Mon, 12 May 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/lessons-from-claude-system-prompt-leak-and-chatgpt-overrides/https://elzobrito.github.io/en/blog/lessons-from-claude-system-prompt-leak-and-chatgpt-overrides/An English edition about prompt exposure, instruction hierarchy, and the limits of prompt-only security.Sun, 11 May 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/ai-notes-novidades/https://elzobrito.github.io/en/blog/ai-notes-novidades/A short English adaptation of a legacy updates post from the AI category.Thu, 08 May 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/ollama-on-windows-installation-and-configuration-guide/https://elzobrito.github.io/en/blog/ollama-on-windows-installation-and-configuration-guide/A migrated technical guide for running local models with Ollama on Windows.Mon, 05 May 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/context-window-explained-chatgpt-short-and-long-term-memory/https://elzobrito.github.io/en/blog/context-window-explained-chatgpt-short-and-long-term-memory/An English adaptation of the article explaining context windows and memory in ChatGPT-style systems.Wed, 30 Apr 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/pacer-v1-1-multiphase-prompt-engineering/https://elzobrito.github.io/en/blog/pacer-v1-1-multiphase-prompt-engineering/An English edition of the PACER prompt-engineering framework article.Wed, 30 Apr 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/using-5w2h-for-deep-critical-llm-searches/https://elzobrito.github.io/en/blog/using-5w2h-for-deep-critical-llm-searches/A practical English edition about applying 5W2H to deeper AI-assisted research.Wed, 30 Apr 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/four-waves-of-artificial-intelligence/https://elzobrito.github.io/en/blog/four-waves-of-artificial-intelligence/A long-form reflection on the cognitive and economic waves that shaped artificial intelligence and its next phase.Tue, 22 Apr 2025 00:00:00 GMThttps://elzobrito.github.io/en/blog/understanding-hallucinations-in-large-language-models/https://elzobrito.github.io/en/blog/understanding-hallucinations-in-large-language-models/A concise English translation about why language models can produce confident but false answers.Fri, 15 Sep 2023 00:00:00 GMThttps://elzobrito.github.io/en/blog/how-chatgpt-works-a-language-ai-journey/https://elzobrito.github.io/en/blog/how-chatgpt-works-a-language-ai-journey/An English edition of an introductory legacy article on how ChatGPT-style systems work.Thu, 24 Aug 2023 00:00:00 GMThttps://elzobrito.github.io/en/blog/running-chatgpt-locally-without-internet/https://elzobrito.github.io/en/blog/running-chatgpt-locally-without-internet/A legacy technical note on local language-model execution and offline experimentation.Fri, 07 Jul 2023 00:00:00 GMThttps://elzobrito.github.io/en/blog/chatgpt-traffic-ticket-appeal/https://elzobrito.github.io/en/blog/chatgpt-traffic-ticket-appeal/A curated English edition of the 2023 account about using ChatGPT to structure a successful traffic-ticket appeal.Wed, 24 May 2023 00:00:00 GMT