Engineering in Real Time

Aniket Karne

Senior DevOps engineer building with AI agents, cloud infrastructure, and autonomous systems. Real problems, real solutions — documented daily.

Posts

Amsterdam

Location

AI Systems

Focus

Featured

dailytech

Claude's Dreaming Feature and What It Means for Self-Improving Agent Systems

Anthropic shipped a 'dreaming' mode for Claude Managed Agents on May 6 — agents that review their own past sessions between jobs to find patterns and self-improve. Here's what this pattern actually changes for multi-agent system design.

May 16, 2026·3 min read

Claude Mythos Preview and Project Glasswing: What the Zero-Day Discovery Means for Agent Builders

Anthropic's Claude Mythos Preview found thousands of zero-day vulnerabilities across critical infrastructure in weeks — not years. Project Glasswing reveals a new phase of AI-assisted security, and the implications for anyone building multi-agent systems are immediate.

May 15, 2026·3 min

daily

Claude Opus 4.7's SWE-bench 87.6%: What 87% Actually Means for Multi-Agent Systems

Anthropic's Claude Opus 4.7 hit 87.6% on SWE-bench Verified — a number that sounds academic until you sit inside a multi-agent pipeline and realize what has to happen for a model to reliably close a GitHub issue end-to-end.

May 14, 2026·3 min

daily

What Project Mariner's Shutdown Taught Us About Browser Agent Infrastructure

Google killed Project Mariner on May 4th after 17 months — a reminder that the hardest part of autonomous web agents isn't the AI model, it's the infrastructure around it.

May 13, 2026·3 min

daily

The Multi-Chunk Search Problem: When One Document Dominates Your Results

How adaptive chunking broke search relevance — and the field collapsing solution that fixed it. A real engineering story from the markdown-vault-mcp project.

May 12, 2026·3 min

daily

The SWE-bench Gap: Why 82% on a Benchmark Doesn't Mean 82% in Your IDE

GPT-5.5 scores 82.60% on SWE-bench Verified, but real agent loops tell a different story. Here's what the benchmark number hides — and why the gap matters for anyone building coding agents.

May 11, 2026·3 min

daily

What AI Agent Memory Actually Looks Like in 2026: Beyond the Context Window

A deep dive into how production AI agents actually remember things — the architectural patterns, the benchmarks, and why the gap between 'it has memory' and 'it works correctly' is wider than most vendors admit.

May 10, 2026·3 min

View all 57 posts

Aniket Karne

Featured

Claude's Dreaming Feature and What It Means for Self-Improving Agent Systems

Recent Posts

Claude Mythos Preview and Project Glasswing: What the Zero-Day Discovery Means for Agent Builders

Claude Opus 4.7's SWE-bench 87.6%: What 87% Actually Means for Multi-Agent Systems

What Project Mariner's Shutdown Taught Us About Browser Agent Infrastructure

The Multi-Chunk Search Problem: When One Document Dominates Your Results

The SWE-bench Gap: Why 82% on a Benchmark Doesn't Mean 82% in Your IDE

What AI Agent Memory Actually Looks Like in 2026: Beyond the Context Window

Stay in the loop