Creators of the Internet's 1st Prompt Engineering Guide. Trusted by 3M Users. Compete for $100K in Largest AI Red Teaming Competition: https://xitter.cf/t.co/AEiLMn2jzy
Joined December 2022
- Tweets2.6K
- Following946
- Followers16.6K
- Likes7.2K
Learn Prompting retweeted
Introducing Horizon from @0rinlabs: the first long-horizon learning benchmark made from real agent logs
- SOTA is 21% on the hardest section
- 7-35M tokens of real agent history per task
- Models are hardly getting better on the hardest tasks
- Humans can score 100%
(1/7)
Learn Prompting retweeted
I think "prompting" will keep being an incredibly high-leverage skill, like writing or public speaking.
It is the skill of talking to agents, mediated by the harness.
My main goal is to grow the bandwidth between humans and agents, to help us understand each other better.
Learn Prompting retweeted
Quality of life updates to @GoogleAIStudio we just shipped (using Gemini):
- You can now (optionally) save a temp chat in the playground
- You can now turn a playground chat into an app in 2 clicks
- Updated colors for playground to add some soul to it
- Simplified the mobile vibe coding UI (chat panel)
- Hide the edit title button for an app unless you hover on it
- Simplify the input text box when vibe coding on both desktop and mobile
- Make sure AI Studio persists the last part of the product you visited (build, playground, dashboard)
- Set a default media resolution in the playground
- Made the diff visualizations more simple in the build UI
- Mobile optimize the feedback and bug UI modal
- Make it easier to see feature chips in Build
- Fix ordering of Search Grounding and Maps Grounding
- Rename the Vibe coding Code Assistant to just Gemini
- Add a STT button in the playground
- Make sure Nano Banana 2 correctly shows the API key popup
- Show all categories in the model drop down for the AI Studio playground without needing to scroll
Many more in the works : ) big thanks to the engineering team and Gemini for partnering on these changes with me!!
Learn Prompting retweeted
Link: learnprompting.org/workshops…
Join us LIVE on April 1st @ 12pm ET to understand the latest updates to @GoogleAIStudio by hearing directly from the team that made them.
Learn Prompting retweeted
100%! The number one way to protect your career from AI is to be the most aggressive user of AI in your field.
RUN AT IT.
Humans evolve with their tools. Keep evolving.
Learn Prompting retweeted
I attended a YC event in summer 2024 and the room was polled on who uses Claude. About 10% of hands went up.
Fast forward to now, when I talk to founders, not only are they all using Claude, but many tell me Claude is what lets their team of 2 build like a team of 10 and that their product wouldn't be anything near what it is without it.
Very inspiring to see the change. There's really never been a better time to build things!
Learn Prompting retweeted
PSA: You can vibe code with Gemini 3 Flash and Gemini 3 Pro for free in Google AI Studio
app.new
Learn Prompting retweeted
Thrilled to announce my completion of the Advanced Prompt Hacking course by @LearnPrompting. I learned about vulnerabilities of Prompt Hacking which expanded my experience on building safer prompts.
Learn Prompting retweeted
We’re expanding Labs—the team behind Claude Code, MCP, and Cowork—and hiring builders who want to tinker at the frontier of Claude’s capabilities.
Read more: anthropic.com/news/introduci…
Learn Prompting retweeted
I’m hiring two [AI builders / Prompt engineers / Model whisperers] in SF, who should I talk to and consider?
Learn Prompting retweeted
How to hijack an AI agent via @SanderSchulhoff
Learn Prompting retweeted
Why securing AI is harder than anyone expected and the approaching AI security crisis with @SanderSchulhoff
Sander is a leading researcher in the field of adversarial robustness, which is the art and science of getting AI systems to do things they shouldn't do, through jail-breaking and prompt injection.
What Sander shares in this conversation is essentially that all of the AI systems we use day to day are open to being tricked into doing things they shouldn’t, that there isn’t really a solution to this problem, and that the companies that try to sell solutions for this are mostly BS.
This conversation has nothing to do with AGI, this is a problem today. And that that the only reason we haven’t seen massive hacks and serious damage from AI tools is so far because they haven’t been given that much power yet, and they aren’t that widely adopted yet. But with the rise of agents (who can take actions on your behalf), and robots, and even AI powered browsers, the risk is going to increase very quickly.
This is a really important topic and that opened my mind, and scared me, and it's something that we all need to have a basic understanding of as AI becomes more prevalent in our lives.
Inside:
🔸 A primer on jailbreaking and prompt injection attacks
🔸 Why AI guardrails don’t work
🔸 Why we haven’t seen major AI security incidents yet (but soon will)
🔸 Why AI browser agents are extremely vulnerable
🔸 The practical steps organizations should take instead of buying ineffective security tools
🔸 Why solving this requires merging classical cybersecurity expertise with AI knowledge
Listen now 👇
• YouTube: youtu.be/J9982NLmTXg
• Spotify: open.spotify.com/episode/0IZ…
• Apple: podcasts.apple.com/us/podcas…
Thank you to our wonderful sponsors for supporting the podcast:
🏆 @datadoghq — Now home to Eppo, the leading experimentation and feature flagging platform: datadoghq.com/lenny
🏆 @getmetronome — Monetization infrastructure for modern software companies: metronome.com/
🏆 @gofundme Giving Funds — Make year-end giving easy: gofundme.com/lenny
Learn Prompting retweeted
This is Gemini 3: our most intelligent model that helps you learn, build and plan anything.
It comes with state-of-the-art reasoning capabilities, world-leading multimodal understanding, and enables new agentic coding experiences. 🧵
Learn Prompting retweeted
Introducing Gemini 3 Pro, the world's most intelligent model that can help you being anything to life.
It is state of the art across most benchmarks, but really comes to life across our products (AI Studio, the Gemini API, Gemini App, etc) 🤯
Learn Prompting retweeted
We partnered w/ @OpenAI, @AnthropicAI, & @GoogleDeepMind to show that the way we evaluate new models against Prompt Injection/Jailbreaks is BROKEN
We compared Humans on @HackAPrompt vs. Automated AI Red Teaming
Humans broke every defense/model we evaluated… 100% of the time🧵
Learn Prompting retweeted
5 years ago, I wrote a paper with @wielandbr @aleks_madry and Nicholas Carlini that showed that most published defenses in adversarial ML (for adversarial examples at the time) failed against properly designed attacks.
Has anything changed?
Nope...
