We have not accounted for the true costs of AI coding
It is time to face the true costs of AI coding. Reliable results require compute, supervision, review and maintenance that our productivity estimates often leave out.
Topic
artificial-intelligence
21 articles in this thread. Browse all topics.
Discussing the Trust Planes of Autonomous AI Work
How to establish trust in autonomous AI systems through identity, secrets management, and continuous assurance.
Stop Prompting Your Agents to Behave: Use Sandboxing Instead
Prompts can shape what an AI agent tries to do. Sandboxing and capability controls determine what it can actually do.
Why Desktop Apps Are Making a Comeback in the Age of AI
The browser won the last decade on reach. AI workloads are local, stateful and long-running, and the browser sandbox was never designed for that. The most serious AI tools of the last two years shipped as desktop apps, and this post argues that is not a coincidence.
Trading Expertise for Quick Answers - The Cost of Cheap Intelligence
Knowing something rare is no longer a moat. Most model answers are disposable by design. Expertise is what still stands after the next model ships: a source you can check, a habit of checking it, and residue that outlives the tab.
Evaluating Overlapping Plugins in Coding Agents
Overlapping plugins complicate attributing coding-agent outcomes to the model or its configuration. This post distinguishes package resolution from per-run behaviour and proposes controlled comparisons using invocation traces, correctness, safety and cost.
Different Types of Wikis and When to Use Them
Code repositories, documents, and agent instructions answer different questions about a software system. This guide maps generated repository wikis, codebase analysis, RAG, linked knowledge wikis, and the Open Knowledge Format to help teams choose the right documentation architecture.
MCP Draft DCR Deprecation: What Client ID Metadata Documents Change
The MCP authorization draft deprecates Dynamic Client Registration as a compatibility fallback, not as an OAuth mechanism globally. Client ID Metadata Documents offer portable, origin-associated metadata, but do not authenticate a running public client. This article explains the operational trade-offs, localhost impersonation risks and metadata-fetch protections that remain.
MCP Client Registration Against Entra ID: The OAuth Proxy Pattern
An OAuth proxy can connect MCP clients to an Entra-backed service while keeping downstream registration separate from upstream application provisioning. This conceptual walkthrough explains the two authorization transactions, per-client consent, token validation and refresh limits that make the proxy a security-critical authorization server.
Structuring Software for Humans, MCP, and Peer Agents
Your UI is just one client now; your apps must now treat humans, LLMs, and peer agents as equal consumers.
The Case for Disproportionate Investments in AI: What Investors Get That We Don't
Corporate AI investment reached $252.3 billion in 2024 and is projected to hit $562 billion by 2026. Is this a bubble, or does it reflect a long-term valuation model that standard metrics fail to capture? This article examines the evidence from both sides.
Beyond Chat: The Dawn of Proactive AI with Active Agents
In this discussion, I introduce "Active Agents," my new project envisioning proactive AI that understands context, anticipates needs, and acts in the background. This concept aligns with a broader movement towards AI designed to enhance productivity by moving beyond simple query-response interactions.
You Do Not always need OCR
OCR vs Text Extraction: When to use each method for document processing to achieve a balance between speed, cost, and accuracy.
Why Limit Yourself to One AI When You Can Chat with Many? Meet Chat4All
Why limit yourself to conversing with just one AI when you can engage with several at once? Meet Chat4All - an innovative open-source app that breaks the norm by allowing users to interact with multiple large language models (LLMs) simultaneously.
From Coder to Collaborator: How AI Is Transforming Roles in Big Data Science and Software Engineering
Discussing the transformative impact of AI on traditional tech roles including data science, machine learning, software engineering, data analytics, and data engineering.
Latest in AI: Google Bard's New Features: Must-Try Enhancements
Discover the latest advancements in AI with Google Bard's new features
Microsoft Build 2025 Keynote: Key Takeaways
Github Coding Agents, Copilot 365 Multi-Agents, Windows MCP Registry, NLWeb, Azure AI Foundry Improvements and more...
RAG vs Hallucinations - Making LLMs more reliable
Reviewing the effectiveness of RAG in mitigating hallucinations in LLMs
Exploring AWS Big Data, Analytics, ML, and Cognitive Services
Read Exploring AWS Big Data, Analytics, ML, and Cognitive Services on CRUD Flow.
OpenAI pushes forward with the introduction of GPT-4-turbo featuring a massive 128k tokens context
The unveiling of OpenAIs GPT-4 Turbo marks a significant milestone in the realm of artificial intelligence and its applications across various sectors including open-source communities, startups, and society at large.
Asking ChatGPT to come up with an efficient and flexible file format for Generative AI prompts
Prompt engineering is a big topic in the age of generative AI. As more use cases are being discovered, it is getting harder and harder to keep prompts organised,