Urgent.News

What's breaking now, across thousands of outlets.

Monday, 17 August 2026 Reading Room

AI

Teach Your Agent to Ask for Help

We keep grading agents on the wrong thing. The demos that get shared are the ones where the agent does everything itself. No hand-offs, no pauses, no human touching the keyboard. Full autonomy, start to finish. It looks like the future. Then you put that same agent on real work, and the trait you were cheering for becomes the thing that scares you. An agent that never stops is an agent that will…

dev.to ·

Agent projects often emphasize autonomy, but the key lies in knowing when to ask for help. Most demos showcase agents working independently without any pauses or human intervention. However, real-world applications reveal that an overconfident agent can cause more harm than good. The ability to recognize when to stop and seek assistance is crucial for successful deployment of autonomous systems.

The assumption that more autonomy is always better is misguided. In fact, it's the agent's capability to know when to pause and seek human input that truly matters. Regulators, such as the EU AI Act, now require demonstrable human intervention points for high-risk autonomous systems. Companies are investing in detecting when an agent deviates from its intended scope, rather than preventing such deviations.

The issue lies in treating autonomy as a single setting rather than a decision made per action. Actions can be categorized into four tiers based on their reversibility and blast radius. Tier 1 actions are read-only and can be safely performed by the agent. Tier 2 actions are reversible and can be undone if needed. Tier 3 actions involve external or third-party systems, requiring review before execution. Tier 4 actions are high-risk and irreversible, necessitating human approval regardless of the agent's confidence.

Confidence in an agent's decision-making is not a reliable indicator of its correctness, especially when stakes are high. For instance, three agents each reporting 90% confidence but only being 75% accurate would result in a system with only 42% reliability. The agent may confidently claim 90% accuracy even when it's wrong. Therefore, relying on an agent's confidence alone is insufficient.

A pause feature, designed as a first-class part of the system, can prevent disastrous outcomes. It should be triggered by high-risk actions and should serialize the agent's state to ensure a clean resume upon approval. The pause should have a timeout, typically set at 30 minutes, and should abort the action if no human response is received within that timeframe. Providing a plain-language summary of the proposed action to the human reviewer helps ensure a quick and informed decision.

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

Read the original at dev.to →

More in AI

The jobs of IT giant employees in the US that were taken over by AI Blue collar workers attracting young people's expectations In the United States, major IT companies have begun to cut jobs as they shift their focus from labor-intensive services to AI. Some young people are turning their attention to blue collar jobs that have relatively good working conditions and high pay. Google's parent company, Alphabet, announced on January 10 that it would cut about 12,000 jobs, or about 6% of its total workforce. The company has been promoting the use of AI in its services, and has introduced AI functions such as automatic response to user inquiries. Microsoft also announced on January 18 that it would cut 10,000 jobs. The company is shifting its focus from services that require a lot of labor, such as Windows and Office, to cloud and AI services. Meta, the parent company of Facebook, also cut 11,000 jobs, or about 13% of its workforce, last November. The company is also focusing on AI, and has developed technologies such as facial recognition and automatic translation. As major IT companies continue to cut jobs, some young people are turning their attention to blue collar jobs. According to a survey by the US Bureau of Labor Statistics, the employment rate for young people aged 20-24 in blue collar jobs such as manufacturing, construction, and transportation was 83.4% in January, higher than the overall employment rate of 62.2% for that age group. The average annual salary for electricians and plumbers is around $60,000, and for carpenters and masons, it is around $50,000. These blue collar jobs often have good working conditions, with regular working hours and paid holidays. In addition, some companies are offering additional benefits, such as free college tuition and apprenticeships. For example, a large construction company in the US offers free college tuition to its employees and their families, and provides apprenticeships for young people who want to become carpenters and electricians. As a result, some young people are choosing to pursue blue collar jobs rather than white collar jobs. "I was interested in working with my hands and making things, so I chose to become an electrician," said a 22-year-old man who graduated from high school and became an electrician. "I like the fact that I can work on a variety of projects and see the results of my work," he said. Another young man, 24, who became a carpenter after graduating from high school, said, "I was attracted to the idea of working outdoors and being able to see the results of my work." "I think blue collar jobs are often misunderstood, but they can be very rewarding," he said. While major IT companies continue to cut jobs and promote the use of AI, blue collar jobs are attracting attention from young people.

·asahi.com

More from Monday 17 August →