Skip to content

Tellian

  • The Harness, Taken Apart. Part 1: Three Agents, Nine Tasks — No Easy Win
    English | Русский The Harness, Taken Apart. Part 1: Three Agents, Nine Tasks — No Easy Win For the past year, the same line keeps coming up about coding agents: it’s not the model that matters, it’s what’s built around it — the rules, tools, and memory bolted on top. The industry calls this the … Continue reading “The Harness, Taken Apart. Part 1: Three Agents, Nine Tasks — No Easy Win”
  • AI speeds up every part of software development — and can slow the whole down
    English | Русский AI speeds up every part of software development — and can slow the whole down Fiona Chen and James Stratton of Harvard went through five years of telemetry from 718 firms: after the switch to AI agents, 30% more lines of code and the same number of closed tasks. Review time in … Continue reading “AI speeds up every part of software development — and can slow the whole down”
  • AI Day: how translating a long sentence grew into ChatGPT
    English | Русский AI Day: how translating a long sentence grew into ChatGPT Twelve years ago a paper came out about machine translation. Step by step, ChatGPT grew out of it. September 1 — the day the school year traditionally starts, Knowledge Day in Russia and much of the post-Soviet world. It also makes a … Continue reading “AI Day: how translating a long sentence grew into ChatGPT”
  • The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them
    English | Русский The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them TL;DR — if you only read this box: Start here: anthropics/skills for a small, production-grade, vetted set. Add glebis/claude-skills (~90 tidy personal skills) if you want more, or obra/superpowers if you want a whole workflow, not … Continue reading “The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them”
  • Language, format, placement: how to write prompts an LLM understands better
    English | Русский Language, format, placement: how to write prompts an LLM understands better I spend my days wrangling big prompts to language models — and the same question keeps coming up: what actually works better? Is it true that if you write tersely, telegraph-style, with no filler, the model both understands more precisely and … Continue reading “Language, format, placement: how to write prompts an LLM understands better”

  • The Harness, Taken Apart. Part 1: Three Agents, Nine Tasks — No Easy Win
  • AI speeds up every part of software development — and can slow the whole down
  • AI Day: how translating a long sentence grew into ChatGPT
  • The Seven Biggest Claude Skills Collections: What’s Inside, Which to Trust, and How to Use Them
  • Language, format, placement: how to write prompts an LLM understands better
  • AI
  • AI Agents
  • CDO
  • Data architecture
  • Data governance
  • Deep Learning
  • Prompt Engineering
  • rag
  • Roles
  • Semantic processing
  • Software Engineering
  • Uncategorized

ai AI in SDLC artificial-intelligence Attention Benchmarking business CDO chatgpt chunking claude-code Claude Code Code Review Coding Agents Context Engineering Data architecture Data governance Developer Tools dmbok DORA dwh ELT embedding ETL hiring History of AI integration knowledge-management llm MCP Mutation Testing Neural Networks productivity Prompts Quality Gates rag repository security semantic-search semantic search skills technology Tokenization Transformers trends writing

Theme: Twenty Sixteen. Tellian Proudly powered by WordPress