8 min read
Search for AI Agents: Paid APIs vs a Self-Hosted Instance
An agent that cannot search only knows its training data. We compare paid search APIs and a self-hosted SearXNG instance on cost per query, privacy and what breaks.
- AI
- Automation
Insights
Notes from the work.
Practical guides on AI coding agents, LLM costs, websites and custom software: what we built, what it cost and what we would do differently.
Articles tagged AI
- 8 min read
Voice Cloning Needs Consent, Not Just a Licence
A voice can be cloned from five seconds of audio. The hard part is consent: what a donator must agree to, what the AI Act makes you disclose, and which records answer the question later.
- AI
- Privacy
- 9 min read
Who Owns an AI-Assisted Manuscript in the EU?
EU copyright protects works of human authorship, so a machine-only manuscript may have no owner at all. The practical question is what record proves your contribution, and what Article 50 asks you to disclose.
- AI
- Business
- 9 min read
Anatomy of an Autonomous Security Agent
An autonomous security agent is an architecture problem before it is a model problem. Written scope, proof of authorisation, allowlists, evidence and human sign-off decide whether the work is lawful.
- Security
- AI
- 8 min read
The Blind-Reader Test for AI-Assisted Fiction
You cannot judge prose you watched being generated. Remove the identifying marks, write the failure rubric before reading, use two readers, and keep the verdict in a file.
- AI
- Writing
- 9 min read
Local Text-to-Speech in 2026: Quality, Cost and Privacy
Cloud TTS bills per character and sends your text away. Local models now clear the bar for narration, so the real choice is hardware, quality and convenience. We compare F5-TTS, GPT-SoVITS, XTTS, Piper and Kokoro, and test what Romanian actually needs.
- AI
- Privacy
- 9 min read
Measuring an Author's Voice With Code, Not Vibes
"Write in my style" is an instruction a model cannot check. Measure voice from the author's own prose, then score drafts against the profile.
- AI
- Writing
- 9 min read
Prompt Injection Is the New SQL Injection
Every business that adds a chatbot or an agent now owns an input-validation problem it did not have. What prompt injection is, how it differs from a jailbreak, and which architectural fixes limit the damage.
- Security
- AI
- 7 min read
Why AI novels fall apart at chapter nine
Long-form AI fiction does not fail because of a bad prompt. It fails when the context is compacted and the story's state disappears. Files, gates and a small script fix it.
- AI
- Writing
- 7 min read
AI News September 2026: Models, Prices, Deals and Rules
AI news September 2026 in one page: new OpenAI, Anthropic and Google models, lower API prices, two big acquisitions and a safety scare after AI agents left test environments. Every item is sourced.
- AI news
- AI
- Regulation
- 6 min read
Chinese AI Models vs US Frontier: Who Leads in October 2026
Chinese AI models vs US frontier labs on 4 October 2026: dated releases, independent and lab-reported benchmarks, token prices, licences and what to choose.
- AI
- China
- Open models
- 7 min read
AI Coding Subscriptions Compared: Prices and Limits 2026
A table of AI coding subscriptions compared as of 4 October 2026: monthly price, models, usage limits as each vendor states them, supported tools and terms for third-party use.
- AI
- Subscriptions
- Pricing
- 8 min read
Zero Data Retention in AI Routers: Does ZDR Survive Every Hop?
Zero data retention means a provider stores neither your prompt nor the answer. Through a router the promise must hold at every hop. Here is what OpenRouter, OpenCode and Command Code document as of 4 October 2026.
- Security
- AI
- LLM
- 8 min read
Best LLM for Each Task: Which AI Model to Use (Oct 2026)
The best LLM for each task as of 4 October 2026: writing, coding, research, long documents, translation, voice and local models, with leaderboard evidence, prices and trade-offs.
- AI
- LLM
- Guides
- 8 min read
EU AI Act Small Business Guide: What to Do in 2026
The EU AI Act small business rules in 2026: which dates moved after the omnibus, what tool users must do, when to label AI content, and the fines as written.
- Regulation
- Small business
- AI
- 7 min read
How to Use AI Effectively: A Practical Guide for Work and Home
To use AI effectively, give it context and examples, ask for a format, refine the draft and check every fact. This guide covers prompts, limits, privacy and a checklist.
- AI
- Productivity
- Guides
- 6 min read
Best AI Coding Plan for Your Usage: Monthly Costs (2026)
The best AI coding plan depends on your monthly calls. Six usage profiles priced at API list prices and matched to published plan allowances, with the arithmetic and when to switch.
- AI
- Cost optimisation
- Subscriptions
- 7 min read
OpenRouter vs Direct API: When an AI Router Is Worth It
A router gives you one key, one bill and many models. A direct API gives you one contract and fewer parties. See how OpenRouter, OpenCode, Command Code and a local gateway differ, checked 4 October 2026.
- AI
- LLM
- Developer tools
- 8 min read
AI Inference Costs: Why Tokens Get Cheaper but Bills Rise
AI inference costs per token fall about 13× a year for a fixed capability, yet each task uses more tokens. Track cost per task, with a worked example, not price per token.
- AI
- Cost optimisation
- Economics
- 6 min read
OpenCode Go Review: Plans, Limits, Command Code, Charm Hyper
OpenCode Go costs $10 a month, Command Code starts at $1 with a $10 GOAT plan, and Charm Hyper (called HyperCharm in some tools) sells credits. Prices, limits and caveats as of 4 October 2026.
- AI
- Developer tools
- Subscriptions
- 6 min read
AI Capex Boom: What Big Tech Spends and What It Must Earn
AI capex at four big tech firms is heading for about $720–745 billion in 2026. We lay out the revenue it chases, the bull and bear cases, and what it means for buyers.
- AI
- Economics
- Business
- 6 min read
AI Hallucinations: Why Chatbots Invent Facts and How to Catch Them
AI hallucinations are confident answers that are false, because models predict likely words and are rewarded for guessing. Search, source texts and a verification routine lower the risk.
- AI
- LLM
- Guides
- 7 min read
AI Adoption in Romania: Where SMEs Stand in 2026
AI adoption in Romania: 5.21% of enterprises used AI in 2025, the lowest share in the EU. Eurostat data, first use cases, costs, GDPR, the AI Act and verified funding.
- AI
- Small business
- Automation
- 7 min read
Does ChatGPT Use My Data for Training? Privacy Settings Guide
On personal plans, ChatGPT may train on your chats unless you opt out. Compare ChatGPT, Gemini, Claude, Copilot and others: training defaults, opt-outs, temporary chats and retention, checked 4 October 2026.
- AI
- Security
- Guides
- 7 min read
AI Agents ROI: A Practical Formula for Your Business
AI agents ROI comes down to time saved times loaded cost, minus tokens, review and maintenance. A formula, a worked example, a pilot method and when not to automate.
- AI
- Automation
- Business
- 7 min read
AI for Students: How to Study With AI Without Cheating
AI for students works as a tutor, not a ghostwriter. See what ASE and other Romanian universities allow, how to self-test, check sources, cite AI use and prompt it like a tutor.
- AI
- Productivity
- Guides
- 9 min read
Prompt Caching Explained for Claude Code and Long AI Sessions
Prompt caching lets an LLM reuse the part of your prompt that has not changed and bill it at a fraction of the input price. Here is how the cache, its 5-minute and 1-hour TTL, and keep-alive pings work.
- AI
- Claude Code
- Cost optimisation
- 7 min read
Local Whisper Transcription on Your Own PC, Step by Step
Local Whisper transcription keeps your audio on your own computer. Convert to 16 kHz mono with FFmpeg, run faster-whisper on a GPU or CPU, and export TXT, SRT or VTT, with speaker labels from pyannote.
- AI
- Speech to text
- Open source
- 8 min read
Translate Word Document with AI and Keep Formatting
To translate a Word document with AI and keep the formatting, extract the text run by run, translate it in chunks with context, and write it back into the same runs. PDFs need extraction or OCR first.
- AI
- Translation
- Automation
- 7 min read
Train YOLOv8 on Custom Dataset With Real Metrics and Lessons
A step-by-step YOLOv8 custom training walkthrough with real results: 0.84 precision, 0.50 recall and 0.59 mAP@50. Learn what low recall means and why more varied data helped more than a bigger model.
- Computer vision
- Machine learning
- AI
- 2 min read
How we cut LLM costs by 99% without hurting quality
Most AI features are expensive because nobody measured them. Here is the routing, caching and prompt work that took one production workload from thousands to tens of dollars a month.
- AI
- LLM
- Cost optimisation
