Urgent.News

600+ sources. One page. See who else covered it.

Editions

Tech

loveyourclanker.org

I created an open web resource for Software Engineers. https://loveyourclanker.org/ It highlights different patterns we can consciously choose use when interacting with our AI Coding tools (a.k.a 'Agents'... a.k.a 'Clankers') to stay in control, maintain quality and sensibly increase efficiency. I was prompted to do this (no pun intended) by observing some pretty alarming signals coming from this…

I have developed an open web platform called loveyourclanker.org to assist software engineers. This resource showcases various techniques for consciously choosing how to interact with AI coding tools, also known as agents or clankers, to maintain control, uphold quality, and efficiently increase productivity. The idea for this platform arose from noticing concerning trends within the software engineering community.

These trends include token leaderboards, pressure to utilize tools for staying current or avoiding redundancy, engineers abandoning tools to preserve their sanity, and engineers departing social events to return to their AI assistants.

Engineers are even creating systems that automate human involvement in development, which the source refers to as "agentic engineering." My aim is to normalize and share the methods by which we utilize these tools, emphasizing that there are multiple approaches to retain greater control and agency. It is my hope that this normalization will foster a more positive environment for software engineers.

If you find this platform useful, please share it with others. If you have differing opinions or would like to contribute, please submit a pull request or contact me directly. All contributions are open-source and non-profit.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — it may contain errors, so check the original before relying on it.

Read the original at dev.to →

More in Tech

I filled my agent's wiki with contradictions. It never gave a wrong answer.

There's a comfortable assumption behind a lot of "agent + knowledge base" work: garbage in, garbage out. Feed an agent a messy, stale, duplicate-ridden wiki and it'll confidently tell users the wrong…

  • Clean wiki led to 100% success rate in providing correct answers
  • Degraded wikis with contradictions resulted in lower success rates
  • Agent hedged or refused answers when faced with contradictions