Insights
Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.
Curated links from external sources — not 360Softy original articles.
Your AI agent has a 128K token context window. You're adding in retrieved documents, conversation history, tool outputs, and system instructions. But the answers are getting worse. You're not alone. Most agent failures in production today are context...
OpenAI doesn't ship defensive product features out of nowhere. When they announced Lockdown Mode for ChatGPT — a setting that explicitly restricts connected tools and integrations to prevent data exfiltration — that's a product team responding to something they've seen happen, or credibly modeled as likely to happen at scale. The signal is clear: LLM-connected tooling is a data exfiltration vector. The question for the rest of us building agentic systems isn't "did OpenAI fix it?" — it's "are we
AI Shrinkflation: Your AI Model Was Quietly Dialed Back The age of token subsidization is over. AI providers are adjusting pricing, throttling capacity, and dialing back model quality — and most users haven't noticed yet. You open your AI coding assistant on a Tuesday morning. Something feels off. The reasoning feels shallower. The context-building you relied on is gone. It's not stopping to read the file before editing it. You aren't imagining it. A senior director at AMD's AI group ran the n
Article URL: https://www.science.org/doi/10.1126/science.aed1630 Comments URL: https://news.ycombinator.com/item?id=48430291 Points: 1 # Comments: 1
Article URL: https://www.bunsenlabs.org/ Comments URL: https://news.ycombinator.com/item?id=48430289 Points: 1 # Comments: 0
Article URL: https://gwern.net/llm-catapult Comments URL: https://news.ycombinator.com/item?id=48430282 Points: 2 # Comments: 0
Article URL: https://www.phoronix.com/news/GNOME-File-Previewer-GTK4 Comments URL: https://news.ycombinator.com/item?id=48430269 Points: 2 # Comments: 0
If you are using AI coding assistants today, chances are you aren't just using one. You might be using Claude Code in the terminal for rapid CLI actions, Gemini CLI for long-context search, and Cursor or Copilot as your main IDE. But there is a major friction point: none of these tools talk to each other. If you configure a Model Context Protocol (MCP) server in Claude, Cursor knows nothing about it. What is Wasla? Wasla is an open-source CLI and daemon that monitors and syncs your agent instruc
Work with 360Softy
Book a free consultation and we will tell you honestly whether we can help.
