LLMs when I ask them for a plan: "this 30-min refactor will take 2 days"
LLMs when I give them the full session trace + hill climb the prompt: r_log of 0.74
context and prompting is everything
AI should earn its keep. Introducing the AI Productivity Guarantee.
If Devin delivers less engineering value than you’re paying for, Cognition will fund your usage until it does, up to $10 million.
It’s time for the AI industry to stop maximizing tokens and start maximizing productive output.
they say you become the average of the five people you spend the most time with, so I've taken some precautions
Ryan @ryanbai is known for his iconic red hoodie, so for his birthday, everyone at @cognition got their own.
Been a blast working on this!
Current AI review tools focus on being an end to end reviewer, but it's also important to augment the human and make it easy for them to understand the code and what's going on.
Give it a try!
Meet Devin Review: a reimagined interface for understanding complex PRs.
Code review tools today don’t actually make it easier to read code. Devin Review builds your comprehension and helps you stop slop.
Try without an account: devinreview.com
More below 👇
we didn’t come up with simulation theory until we invented computers. makes me wonder about all the theories we can’t even currently imagine because the tech isn’t there yet.
Agents are starting to get scarily good at computer use... It's soon gonna be a massive game changer in the way people use Devin.
Windsurf feels sooo much nicer to use than a couple weeks ago. Also super excited about where we’re heading, a lot to explore in the IDE space!
Darn almost can’t believe it’s my last IOI already. Huge thanks to @rpeng233 for coaching and supporting me over these years ❤️.
Cognition is the first AI lab to win a verified gold medal at the IOI. Our human, ryanbAI (@ryanbai), placed 7th overall. Impressively, ryanbAI competed under the exact same conditions as all human contestants.
Was wondering when the perfect score would happen. Well deserved!
