Premium Only Content

ChatGPT: This AI has a JAILBREAK?! (Unbelievable AI Progress)
#chatgpt #ai #openai
ChatGPT, OpenAI's newest model is a GPT-3 variant that has been fine-tuned using Reinforcement Learning from Human Feedback, and it is taking the world by storm!
Sponsor: Weights & Biases
https://wandb.me/yannic
OUTLINE:
0:00 - Intro
0:40 - Sponsor: Weights & Biases
3:20 - ChatGPT: How does it work?
5:20 - Reinforcement Learning from Human Feedback
7:10 - ChatGPT Origins: The GPT-3.5 Series
8:20 - OpenAI's strategy: Iterative Refinement
9:10 - ChatGPT's amazing capabilities
14:10 - Internals: What we know so far
16:10 - Building a virtual machine in ChatGPT's imagination (insane)
20:15 - Jailbreaks: Circumventing the safety mechanisms
29:25 - How OpenAI sees the future
References:
https://openai.com/blog/chatgpt/
https://openai.com/blog/language-model-safety-and-misuse/
https://beta.openai.com/docs/model-index-for-researchers
https://scale.com/blog/gpt-3-davinci-003-comparison#Conclusion
https://twitter.com/johnvmcdonnell/status/1598470129121374209
https://twitter.com/blennon_/status/1597374826305318912
https://twitter.com/TimKietzmann/status/1598230759118376960/photo/1
https://twitter.com/_lewtun/status/1598056075672027137/photo/2
https://twitter.com/raphaelmilliere/status/1598469100535259136
https://twitter.com/CynthiaSavard/status/1598498138658070530/photo/1
https://twitter.com/tylerangert/status/1598389755997290507/photo/1
https://twitter.com/amasad/status/1598042665375105024/photo/1
https://twitter.com/goodside/status/1598129631609380864/photo/1
https://twitter.com/moyix/status/1598081204846489600/photo/2
https://twitter.com/JusticeRage/status/1598959136531546112
https://twitter.com/yoavgo/status/1598594145605636097
https://twitter.com/EladRichardson/status/1598333315764871174
https://twitter.com/charles_irl/status/1598319027327307785/photo/4
https://twitter.com/jasondebolt/status/1598243854343606273
https://twitter.com/mattshumer_/status/1598185710166896641/photo/1
https://twitter.com/i/web/status/1598246145171804161
https://twitter.com/bleedingedgeai/status/1598378564373471232
https://twitter.com/MasterScrat/status/1598830356115124224
https://twitter.com/Sentdex/status/1598803009844256769
https://twitter.com/harrison_ritz/status/1598828017446371329
https://twitter.com/parafactual/status/1598212029479026689
https://www.engraved.blog/building-a-virtual-machine-inside/
https://twitter.com/317070
https://twitter.com/zehavoc/status/1599193444043268096
https://twitter.com/yoavgo/status/1598360581496459265
https://twitter.com/yoavgo/status/1599037412411596800
https://twitter.com/yoavgo/status/1599045344863879168
https://twitter.com/natfriedman/status/1598477452661383168
https://twitter.com/conradev/status/1598487973351362561/photo/1
https://twitter.com/zswitten/status/1598100186605441024
https://twitter.com/CatEmbedded/status/1599141379879600128/photo/2
https://twitter.com/mattshumer_/status/1599175127148949505
https://twitter.com/vaibhavk97/status/1598930958769860608/photo/1
https://twitter.com/dan_abramov/status/1598800508160024588/photo/1
https://twitter.com/MinqiJiang/status/1598832656422432768/photo/2
https://twitter.com/zswitten/status/1598088280066920453
https://twitter.com/m1guelpf/status/1598203861294252033/photo/1
https://twitter.com/SilasAlberti/status/1598257908567117825/photo/1
https://twitter.com/gf_256/status/1598962842861899776/photo/1
https://twitter.com/zswitten/status/1598088267789787136
https://twitter.com/gf_256/status/1598178469955112961/photo/1
https://twitter.com/samczsun/status/1598564871653789696/photo/1
https://twitter.com/haus_cole/status/1598541468058390534/photo/3
https://twitter.com/tailcalled/status/1599181030065246208/photo/1
https://twitter.com/pensharpiero/status/1598731292278865920
https://twitter.com/sleepdensity/status/1598233414683197441
https://twitter.com/goodside/status/1598253337400717313
https://twitter.com/Carnage4Life/status/1598332648723976193/photo/2
https://github.com/sw-yx/ai-notes/blob/main/TEXT.md#jailbreaks
https://twitter.com/dannypostmaa/status/1599352584963170309/photo/4
https://twitter.com/sama/status/1599112749833125888
https://twitter.com/sama/status/1599114807474810884
https://twitter.com/sama/status/1599461195005587456
https://twitter.com/deliprao/status/1599451192215887872
https://twitter.com/michlbrmly/status/1599168681711656961
https://twitter.com/zoink/status/1599281052115034113
Links:
https://ykilcher.com
Merch: https://ykilcher.com/merch
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://ykilcher.com/discord
If you want to support me, the best thing to do is to share out the content :)
If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
-
LIVE
FreshandFit
2 hours agoCall-In Show
2,859 watching -
4:27:46
Nerdrotic
7 hours ago $31.93 earnedDaredevil Born Again REVIEW, Harry Potter Show DOA, DC HACKED! | Friday Night Tights 344 Paul Chato
95.5K29 -
1:15:15
Glenn Greenwald
3 hours agoWeek in Review: Lee Fang and Leighton Woodhouse on Ukraine War and NYT Piece Revealing Tensions within Trump Admin; PLUS: Lee Fang Takes Audience Questions on DOGE and Big Tech | SYSTEM UPDATE #420
41K35 -
1:03:30
Sarah Westall
6 hours agoMassive Government Overhaul: FBI, CIA, IRS and more to be Gutted w/ Sam Anthony
53.3K13 -
1:07:40
IsaacButterfield
6 hours ago $1.35 earnedAustralia Under Attack | Trump's State of the Union | All LGBTQ Cast (W Guest Frenchy)
17.6K -
1:23:37
Edge of Wonder
5 hours agoIs Your Car Collecting Your Biodata? Whistleblower Exposes Dark Agenda
21.5K2 -
2:08:50
Quite Frankly
8 hours ago"News Round-Up, Celebrity Stories, Friday Extras" ft. J Gulinello 3/7/25
27.9K5 -
55:49
LFA TV
1 day agoGermany Started Two World Wars and Now Wants Nuclear Weapons | TRUMPET DAILY 3.7.25 7PM
26.8K23 -
1:34:38
2 MIKES LIVE
4 hours ago2 MIKES LIVE #189 Open Mike Friday (Sort Of)
20.6K -
1:48:14
Right Side Broadcasting Network
12 hours agoLIVE REPLAY: President Trump Delivers Remarks at The White House Digital Assets Summit - 3/7/25
142K42