Posts by galian
@galian
Galian
Founder of Cursuri-AI.ro and Co-Founder of ProtectAds.com. Passionate about scal...
Comments by galian
Claude Haiku 5.5 shipped on October 7, 2026 with a headline price of $0.10 per million input tokens and $0.50 per million output tokens, a tenth of the per-token price of Claude Haiku 4.5. The headline has a condition. Those prices apply to requests ...
The agent was twenty minutes into a migration task. It had read the schema, planned eleven steps, executed six of them — two of which wrote to production — and was waiting on the model for step seven when the pod was rescheduled.
Everything the agen...
The agent was twenty minutes into a migration task. It had read the schema, planned eleven steps, executed six of them — two of which wrote to production — and was waiting on the model for step seven when the pod was rescheduled.
Everything the agen...
Every team that ships an agent has the same week-three conversation. The agent picks the wrong tool. It calls three tools where one would do. It burns forty thousand tokens reading things it will never use. Somebody says "the model isn't smart enough...
Every team that ships an agent has the same week-three conversation. The agent picks the wrong tool. It calls three tools where one would do. It burns forty thousand tokens reading things it will never use. Somebody says "the model isn't smart enough...
The support ticket says "the assistant took forever and then gave up." You open your logs. There's a line that says calling model..., a line eleven seconds later that says done, and somewhere in between, three tool calls that logged nothing because t...
Your LLM App Works Until It Doesn't — Handling Rate Limits, Timeouts, and Overloaded APIs in Product
Your LLM App Works Until It Doesn't — Handling Rate Limits, Timeouts, and Overloaded APIs in Production
Your LLM feature worked flawlessly for weeks. Then you got your first traffic spike — a newsletter mention, a busy Monday — and the logs filled ...
You built a RAG system. You embedded your docs, wired up a vector store, stuffed the top chunks into the prompt, and shipped. Then the questions came back wrong — confidently, fluently wrong — and your first instinct was to blame the model or reach f...
Most RAG tutorials quietly ship your documents to someone else's cloud. You paste a contract, a customer list, or an internal wiki into an embedding API, and that data now lives on a server you don't control, in a jurisdiction you didn't choose. For ...
Most RAG tutorials quietly ship your documents to someone else's cloud. You paste a contract, a customer list, or an internal wiki into an embedding API, and that data now lives on a server you don't control, in a jurisdiction you didn't choose. For ...
> TL;DR — Model Context Protocol MCP is Anthropic's open standard for connecting LLMs to external tools, data sources, and services. It's powerful, but it's also overhyped. This guide covers what MCP actually is under the hood, when it's the right ar...
Every CRM vendor on the planet has rebranded itself as "AI-first." HubSpot has Breeze AIhttps://www.hubspot.com/products/artificial-intelligence, Salesforce has Einsteinhttps://www.salesforce.com/artificial-intelligence/, Zoho has Ziahttps://www.zoho...
The global AI race is accelerating — and countries that fail to upskill their workforce risk falling behind permanently. While Western Europe and the US dominate AI adoption, Romania is writing its own chapter in the story, thanks to a bold EdTech in...
chevron_left