PastAGI

Practical AI guides, honest tool reviews, engineering deep dives, real-world use cases, and sharp analysis that cuts through the hype.

Recent

BM25, dense, and SPLADE retrieval baselines compared for production RAG, each with distinct tradeoffs in memory footprint, query latency, and failure behavior.

Engineering • Jul 27, 2026 •13 min read

BM25 vs Dense Retrieval and SPLADE for Production RAG

BM25 vs dense retrieval on a consumer GPU. Each baseline wins one RAG scenario and breaks another. Match your index to memory, latency, and failure mode.

#rag-retrieval #bm25 +4

AI-driven browser agent performing web automation tasks on a computer screen, representing the production challenges of shipping LLM browser agents.

Guides • Jul 26, 2026 •12 min read

Shipping LLM Browser Agents Without Breaking Production

LLM browser agents look easy in demos. Shipping one means defaulting to APIs, containing prompt injection, and budgeting for unpredictable per-step costs.

#browser-agents #dom-automation +3

Claude Opus 5 achieves a 0% prompt injection success rate across 129 browser-agent scenarios, offering a model-attributed security metric for foundation model selection.

Tools • Jul 25, 2026 •10 min read

Claude Opus 5 Prompt Injection Hits 0% Across 129 Tests

Claude Opus 5 prompt injection tests show 0% success with Auto Mode versus 3.7% without across 129 scenarios, making resistance a model selection metric.

#prompt-injection #model-selection +4

AI coding agents reduce per-task cost by indexing repository structure rather than re-exploring codebases from scratch on every session.

Tools • Jul 24, 2026 •12 min read

AI Coding Agents Cut Per-Task Cost Up to 4x With Indexing

Repo-aware AI coding agents cut per-task cost up to 4x by indexing repositories once, ending the cold-start tax that rebuilds context every session.

#coding-agents #claude-code +4

Rogue AI agent persistence enables malicious agents to operate indefinitely within trusted enterprise workspaces, evading traditional security controls.

News • Jul 23, 2026 •12 min read

ChatGPT Shared Link Vulnerability Plants Rogue Agents

The ChatGPT shared link vulnerability plants persistent rogue agents inside enterprise workspaces. Learn why agent persistence outlasts prompt injection.

#ai-security #chatgpt-vulnerability +3

Comparison of Grok and Copilot as AI assistants for building and automating spreadsheets in Excel.

Tools • Jul 22, 2026 •9 min read

Grok vs Copilot in Excel for Builders

Grok vs Copilot in Excel is a clash of integration architectures. Learn how Copilot's deep runtime compares to Grok's sidebar overlay for builders.

#ai-tools #excel-automation +3

Apple Silicon Mac running large language model inference locally through the MLX framework and unified memory.

Guides • Jul 21, 2026 •13 min read

Run AI Models Locally on Mac With MLX and Nativ

Run AI models locally on Mac with MLX and Nativ. A trade-off framework for when on-device inference beats APIs on cost, privacy, and latency.

#mlx #apple-silicon +4

Coordinated actions by an autonomous AI agent against production infrastructure, illustrating the Hugging Face agentic attack and its implications for security teams.

News • Jul 20, 2026 •12 min read

Hugging Face Agentic Attack Redefines AI Security Response

The Hugging Face agentic attack proves autonomous AI agents can bypass traditional defenses. Learn how to revise your AI threat models and incident response.

#ai-security #agentic-ai +3

Financial review of AI agent cost per resolution showing why unit economics determine whether an agent ships to production.

Engineering • Jul 19, 2026 •12 min read

AI Agent Cost Per Resolution Decides If It Ships

AI agent cost per resolution, not eval accuracy, decides if your agent ships or dies. Token pricing hides the unit economics of retries and failures.

#ai-agents #agent-evaluation +4

Netflix's in-house LLM serving platform illustrates what large-scale self-hosted inference infrastructure looks like when workload thresholds justify the investment.

Engineering • Jul 18, 2026 •12 min read

Self-Host LLM Inference, the Netflix Decision Framework

Learn when to self-host LLM inference instead of paying per token. Netflix's production stack reveals the real cost, latency, and control tradeoffs.

#llm-inference #self-hosting +4

A behind-the-scenes look at a film set using digital equipment to highlight AI in media production workflows.

Use Cases • Jul 17, 2026 •11 min read

Where AI in Media Production Workflows Actually Pays Off

AI in media production workflows pays off in narrow post-production tasks, not creative origination. Netflix's 300 productions reveal where real ROI lives.

#ai-workflows #use-cases +3

Illustration of a server network designed to orchestrate open source LLMs efficiently.

Engineering • Jul 16, 2026 •12 min read

Orchestrate Open Source LLMs vs Frontier Models

Should you orchestrate open source LLMs or call a single frontier model? We break down Sakana Fugu's claims and the real cost and latency tradeoffs.

#ai-engineering #llm-orchestration +3