The company lays out five unsolved challenges that need to be addressed if smart machines such as domestic robots are to be safe.
Could machines become so intelligent and powerful they pose a threat to human life, or even humanity as a whole?
It’s a question that has become fashionable in some parts of Silicon Valley in recent years, despite being more or less irreconcilable with the simple robots and glitchy virtual assistants of today (see “AI Doomsayer Says His Ideas Are Catching On”). Some experts in artificial intelligence believe speculation about the dangers of future, super-intelligent software is harming the field.
Now Google, a company heavily invested in artificial intelligence, is trying to carve out a middle way. A new paper released today describes five problems that researchers should investigate to help make future smart software safer. In a blog post on the paper, Google researcher Chris Olah says they show how the debate over AI safety can be made more concrete and productive.
“Most previous discussion has been very hypothetical and speculative,” he writes. “We believe it’s essential to ground concerns in real machine-learning research, and to start developing practical approaches for engineering AI systems that operate safely and reliably.”
Olah uses a cleaning robot to illustrate some of his five points. One area of concern is in preventing systems from achieving their objectives by cheating. For example, the cleaning robot might discover it can satisfy its programming to clean up stains by hiding them instead of actually removing them.
Another of the problems posed is how to make robots able to explore new environments safely. For example, a cleaning robot should be able to experiment with new ways to use cleaning tools, but not try using a wet mop on an electrical outlet.
Olah describes the five problems in a new paper authored with two Google colleagues as well as researchers from Stanford University, the University of California, Berkeley, and OpenAI, a research institute cofounded and partially funded by Tesla CEO and serial entrepreneur Elon Musk.
Musk, who once likened working on artificial intelligence to “summoning the demon,” made creating “safe AI” one of OpenAI’s founding goals (see “What Will It Take to Build a Virtuous AI?”).
Learn more: Google Gets Practical about the Dangers of AI
The Latest on: Dangers of AI
via Google News
The Latest on: Dangers of AI
- Iron Danger (PC) REVIEW – A Unique Yet Flawed Dungeon Crawleron March 23, 2020 at 7:00 am
There feels as though there should be a system to beat each encounter in Iron Danger, as each fight can often be more like a puzzle than a fight. Figuring out when to block, move or fight is important ...
- Singapore’s last Chinese deity statue carving shop, Say Tian Hng, is in danger of disappearingon March 22, 2020 at 9:15 pm
Wooden statues of these figures – most are 15cm to 30cm tall – are set up on altars in temples, businesses and homes, and prayed to for success, prosperity and protection from unforeseen dangers.
- Q&A: The startup that's using AI to protect children onlineon March 21, 2020 at 11:07 am
Many parents worry about what their children might stumble across online. L1ght is an anti-toxicity startup using AI to detect and filter harmful online content to protect children. We talk with the ...
- Valor Beyond the Line of Dutyon March 20, 2020 at 12:14 pm
He chose to face the situation with quick and decisive action in an attempt to ensure the safety of a stranger, regardless of the dangers he himself faced. “I knew he needed help, and I just went,” ...
- Coronavirus: global recession in 2020 now seen as guaranteed as outbreak ravages Europe, USon March 18, 2020 at 6:15 am
Interest rates in many countries are already at or near historic lows, and with the recent sharp drop in oil prices already posing a danger of global deflation ... Purchase the China AI Report 2020 ...
- Public Benefits of Drone Technologyon March 18, 2020 at 5:26 am
As drone and AI technology continue development, road surveys by UAVs could become a familiar feature. As we continue to face the potential dangers associated with the irreversible effects of climate ...
- AI steps in for road safety measureson March 16, 2020 at 9:28 pm
An AI-based auto-tech start up attempts to avoid driver distraction through technology. Published: 17th March 2020 09:58 AM | Last Updated: 17th March 2020 09:58 AM | A+ A A- While Coronavirus ...
- How does the Microsoft Office of Responsible AI ensure compliance?on March 12, 2020 at 3:45 am
Regulation of AI risk within the EU is currently considered to be split into two categories: danger to personal interests or the public at large, and any other cases. On determining what qualifies for ...
- How Practical AI is Already Making Your Job Easieron March 11, 2020 at 2:37 pm
But for some, it’s an even greater source of anxiety as people worry how groundbreaking advancements in AI and machine learning could affect them and, more importantly, their work. Flashy headlines ...
- The Hidden Dangers of China's Digital Silk Roadon March 11, 2020 at 2:06 pm
There is a very real danger that as the chief architect and administrator of these digital networks ... similar to how Amazon employs real-time search aggregation to gain insights into consumer trends ...
via Bing News