GROUNDBREAKING AI Security Discovery! Top Researcher

Dr. David J Miller, a leading AI researcher-and my former college roommate!-gives us a masterclass in cutting edge Artificial Intelligence security research, including techniques never before made public!
This one gets way into the weeds but shows how amazing AI research is-and how important it can be to our everyday lives and trust in the ever growing power of AI.
**If you are looking to purchase a new Tesla Car, Solar roof, Solar tiles or PowerWall, just click this link to get up to $500 off! www.tesla.com/referral/john11286. Thank you!
If you'd like to contact David, you can reach him at: [e-mail]
Join this channel to get access to perks:
/ @drknowitallknows
**To become part of our Patreon team, help support the channel, and get awesome perks, check out our Patreon site here: / drknowitallknows . Thanks for your support!
How Can We Trust AI?! AI Security Expert Explains!
Go to drinkag1.com/drknowitall to get started on your first purchase and receive a FREE 1-year supply of Vitamin D3+K2 and 5 travel packs.
Get The Elon Musk Mission (I've got two chapters in it) here:
Paperback: amzn.to/3TQXV9g
Kindle: amzn.to/3U7f7Hr!
**Want some awesome Dr. Know-it-all merch, including the AI STUDENT DRIVER Bumper Sticker? Check out our awesome Merch store: drknowitall.itemorder.com/sale
For a limited time, use the code "Knows2021" to get 20% off your entire order!
**Check out Artimatic: www.artimatic.io
**You can help support this channel with one click! We have an Amazon Affiliate link in several countries. If you click the link for your country, anything you buy from Amazon in the next several hours gives us a small commission, and costs you nothing. Thank you!
* USA: amzn.to/39n5mPH
* Germany: amzn.to/2XbdxJi
* United Kingdom: amzn.to/3hGlzTR
* France: amzn.to/2KRAwXh
* Spain: amzn.to/3hJYYFV
**What do we use to shoot our videos?
-Sony alpha a7 III: amzn.to/3czV2XJ
--and lens: amzn.to/3aujOqE
-Feelworld portable field monitor: amzn.to/38yf2ah
-Neewer compact desk tripod: amzn.to/3l8yrUk
-Glidegear teleprompter: amzn.to/3rJeFkP
-Neewer dimmable LED lights: amzn.to/3qAg3oF
-Rode Wireless Go II Lavalier microphones: amzn.to/3eC9jUZ
-Rode NT USB+ Studio Microphone: amzn.to/3U65Q3w
-Focusrite Scarlette 2i2 audio interface: amzn.to/3l8vqDu
-Studio soundproofing tiles: amzn.to/3rFUtQU
-Sony MDR-7506 Professional Headphones: amzn.to/2OoDdBd
-Apple M1 Max Studio: amzn.to/3GfxPYY
-Apple M1 MacBook Pro: amzn.to/3wPYV1D
-Docking Station for MacBook: amzn.to/3yIhc1S
-Philips Brilliance 4K Docking Monitor: amzn.to/3xwSKAb
-Sabrent 8TB SSD drive: amzn.to/3rhSxQM
-DJI Mavic Mini Drone: amzn.to/2OnHCEw
-GoPro Hero 9 Black action camera: amzn.to/3vgVMrH
-GoPro Max 360 camera: amzn.to/3nORGYk
-Tesla phone mount: amzn.to/3U92fl9
-Suction car mount for camera: amzn.to/3tcUfRK
-Extender Rod for car mount camera: amzn.to/3wHQXsw
**Here are a few products we've found really fun and/or useful:
-NeoCharge Dryer/EV charger splitter: amzn.to/39UcKWx
-Lift pucks for your Tesla: amzn.to/3vJF3iB
-Emergency tire fill and repair kit: amzn.to/3vMkL8d
-CO2 Monitor: amzn.to/3PsQRh2
-Camping mattress for your Tesla model S/3/X/Y: amzn.to/3m7ffef
**Music by Zenlee. Check out his amazing music on instagram -@zenlee_music
or TH-cam - / @zenlee_music
Tesla Stock: TSLA
**EVANNEX
Check out the Evannex web site: evannex.com/
If you use my discount code, KnowsEVs, you get $10 off any order over $100!
**For business inquiries, please email me here: [e-mail]
Twitter: / drknowitall16
Also on Twitter: @Tesla_UnPR: / tesla_un
Instagram: @drknowitallknows
**Want some outdoorsy videos? Check out Whole Nuts and Donuts: / @wholenutsanddonuts5741

[@mattsenkow6986]

Damn it's good to hear you two talking about AI comp sci. I've worried about saboteurs messing with Tesla's data set for years. It's good to see an approach for dealing with poisoned data. Thanks Dr. Miller!

[@dan_chay]

I enjoyed this interview a lot. Thank you both.

[@appl314]

I smiled at something being touted as new, but has been around decades earlier. ...I've been in IT for 45 years... sometimes it feels like there is nothing new under the sun... just a new audience and a new twist. ...but we keep moving forward

[@Tinman_56]

Very true. Many of these "new ideas" are just older ideas renamed by recent generations because they believe their new terminology is leaps and bounds ahead of the "old tjmers!" The one thing I'd like to see go away, imo, is using PowerPoint presentations in discussions on TH-cam. 🥱🥱

[@Digital-Dan]

When Unix started to take over in the universities, a colleague noted that one could republish any earlier systems result, applied in the Unix domain, as new work. 🙂 I guess that happens repetitively over time, or even maybe recursively.

[@jackcoats4146]

As much as my eyes are glossing over, the old school geek in me it head over heels excited about this kind of research and information. John, keep up getting this kind of input if you can, it makes me feel like I am back in touch with really current things again. If this is hammered by the algorithm, I suggest start a secondary channel for this kind of info to give a more rigorous pipeline of this kind of more learned information.

[@jimparr01Utube]

I concur good Sir. As retired engineer, I have done some rather cool things with low level uP instruction sets & interpreter languages that I was proud off at the time. But this AI stuff is so many levels above my understanding, I can glean very little from such a discussion. Still, I find it fascinating.
The poisoning susceptibility of advanced neural-net models is especially intriguing - and I suppose a little worrying.

[@jamesh318]

In Terminator 3, wasnt skynet turned on to deal with a computer virus? 😅

[@chuckm651]

You two doctors did a great job discussing this complex topic, but you both agreed to have John advance the slides in the presentation because it was too difficult to figure out a way for the guest to do it. Yep, been there. 😂

[@fteoOpty64]

For a second I really thought it was Charlie Miller!!!.

[@AquarianSoulTimeTraveler]

Yeah I would say just by its fundamental nature a large language model that predicts what word or character should come next ultimately isn't based out of logical deduction it's just piecing words together.

[@JMeyer-qj1pv]

That's was thought provoking. I didn't realize it was so easy to poison a model that way. Unbounded activation functions do seem like the root of the problem so it would be a good idea to reign them in. But as we stamp out misclassifications, it's going to make bot detection more difficult.

[@Digital-Dan]

We should also plan on reining them in.

[@JaredFarrer]

Where’s the discovery

[@montypalmer4556]

I hope this guy doesn't reveal secrets to enemies. Enrico Fermi inadvertently let the successful atomic bomb out while speaking to non experts in Los Alamos one evening (at my ex's uncle's house). It created quite a stir since a reporter was there!

[@yourlogicalnightmare1014]

Sounds like a fantastic argument for why AI will never be trustworthy and probably of far less utility than people expect

[@Digital-Dan]

Well, human reasoning is subject to noise interference as well, or more so?

[@ericswenson7468]

Compute is the only limitation now. Elon's statement on realistic video accomplished last year confirms this th-cam.com/video/6Xv6uSeXbJ4/w-d-xo.htmlsi=uV_xS2mfzasum-bk where video replication of reality is equal to AGI achievement. Only compute is the limitation now.

[@coryparker7645]

😂