The Download: tricking LLMs, and reviving geothermal plants
At a glance
This is today’s edition of The Download , our weekday newsletter that provides a daily dose of what’s going on in the world of technology. A fundamental flaw leaves LLMs strikingly vulnerable to attack It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they wo
- Primary source
- MIT Technology Review — Read original article
- Published
- Topic
- General
This is today’s edition of The Download , our weekday newsletter that provides a daily dose of what’s going on in the world of technology.
A fundamental flaw leaves LLMs strikingly vulnerable to attack It is impossible to make large language models fully secure against hacks because of a fundamental flaw in how they work, a team of researchers argue in a paper presented at a top AI conference earlier this month.
The flaw concerns how LLMs identify who or what is giving them instructions.
By taking advantage of it, the researchers were able to make popular LLMs spit out information they had been trained not to provide, such as how to synthesize cocaine and how to sabotage a commercial aircraft’s navigation system.
Read our story about the flaw the researchers found, its implications—and why it may never be fixed. —Will Douglas Heaven How an overlooked geothermal plant got a second chance In June 2024, a small company called Zanskar purchased a geothermal power plant in New Mexico that was failing fast.
The water coming from the underground reservoir was getting colder by the day, making the plant uneconomical to run. Now, two years later, that plant is running at full capacity again
This summary comes from MIT Technology Review. Read the full article at the original source.