teddyntran Profile Banner
Teddy Profile
Teddy

@teddyntran

Followers
1K
Following
77K
Media
525
Statuses
11K

AI Red Team ~~~ Informatics @sjsu Data Architecture @northropgrumman All opinions and views are my own.

Sunnyvale, CA
Joined April 2013
Don't wanna be here? Send us removal request.
@teddyntran
Teddy
2 years
Really happy I got to take my dad to this game ❤️
2
0
34
@lilianweng
Lilian Weng
5 days
I’ve been telling people this a lot today: I enjoy so much working with people who care about what they are building and craftsmanship. It is a privilege to have a chance to work on something I’m passionate about, beyond making a living. I cherish it and don’t take it for
52
53
1K
@teddyntran
Teddy
28 days
Its so crazy how true this is….
@bluewmist
blue
30 days
btw in your 20's and 30’s you’ll start rediscovering the niche interests and hobbies you had as a kid. it’s very important you revisit them. your younger self was actually on to something.
0
0
1
@valent1nee
Valentino Massaro
2 months
I'm really excited to share my first research article related to hacking Google Gemini! https://t.co/e7GcJuGLCb #bugSWAT #GoogleVRP
9
103
488
@karpathy
Andrej Karpathy
11 months
Agency > Intelligence I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are
@garrytan
Garry Tan
11 months
Intelligence is on tap now so agency is even more important
2K
9K
50K
@hayesdev_
Hayes
3 months
This guy literally dropped the best life advice you’ll ever hear
673
21K
135K
@karpathy
Andrej Karpathy
3 months
Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,
702
3K
24K
@teddyntran
Teddy
5 months
I don’t even know how to feel. This is truly the worst I’ve ever felt being a United fan. For 20+ years I’ve supported this team and I just don’t know how to feel anymore.
@FabrizioRomano
Fabrizio Romano
5 months
🚨 4th division side Grimsby Town have eliminated Man United from the Carabao Cup.
0
0
0
@ManUtd
Manchester United
12 years
David Moyes says #mufc must improve in a number of areas, including passing, creating chances and defending.
2K
25K
35K
@teddyntran
Teddy
5 months
Being a Manchester United fan is simply not possible.
0
0
1
@simonw
Simon Willison
5 months
I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, MCP security and the lethal trifecta. Here are the annotated slides from my presentation, including notes on my weird hobby of trying to coin or amplify new terms of art
Tweet card summary image
simonwillison.net
I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, the lethal trifecta and the challenges of securing systems that use MCP. It wasn’t …
23
57
409
@teddyntran
Teddy
6 months
Professor Valens
@valens
Soham
6 months
Raise Your Bet, Outgrow Regret You can frag out or write clean code, but if you're still running the same aim routine, the same comm habits, and the same workflow, you're not growing as much as you're just reinforcing what you already know. At some point, skill alone stops
0
0
0
@kamithecreator_
100gbps
7 months
just contributed my first "no, nothing from my end" in a work meeting
104
5K
92K
@jiratickets
JT
7 months
IT employees when you submit a ticket after you messaged them for help and they told you to submit a ticket
459
13K
235K
@teddyntran
Teddy
7 months
CS2 is so back
3
0
2
@AnthropicAI
Anthropic
7 months
New Anthropic Research: A new set of evaluations for sabotage capabilities. As models gain more agentic abilities, we need to get smarter in how we monitor them. We’re publishing a new set of complex evaluations that test for sabotage—and sabotage-monitoring—capabilities.
59
228
2K
@karpathy
Andrej Karpathy
7 months
RT to help Simon raise awareness of prompt injection attacks in LLMs. Feels a bit like the wild west of early computing, with computer viruses (now = malicious prompts hiding in web data/tools), and not well developed defenses (antivirus, or a lot more developed kernel/user
@simonw
Simon Willison
7 months
If you use "AI agents" (LLMs that call tools) you need to be aware of the Lethal Trifecta Any time you combine access to private data with exposure to untrusted content and the ability to externally communicate an attacker can trick the system into stealing your data!
100
527
3K
@arithmoquine
henry
8 months
> be apple > richest company in the world, every advantage imaginable > go all in on AI, make countless promises > get immediately lapped by everyone > 2 years into the race, nothing to show for it > give up, write a paper about how it's all fake and gay and doesn't matter anyway
@wolfejosh
Josh Wolfe
8 months
Apple just GaryMarcus'd LLM reasoning ability
396
2K
33K
@Baxate
Baxate
8 months
this ending felt so inevitable that it almost ruins the enjoyment of the plot for being too predictable
3
2
178
@ThePrimeagen
ThePrimeagen
8 months
when you first understand recursion
66
240
5K
@anuatluru
anu
8 months
The hustle bros & the harmony bros are both wrong. This is the right mindset: “You mentioned sacrifices, about all the things that you lost to become professional. I never had the feeling that I did a lot of sacrifices. I just was not able to do all the things that my friends
13
83
1K