Lemma (@uselemma_ai) helps AI agents learn from real-world use, so they get better instead of breaking over time. They turn user feedback into automated prompt improvements, so teams can focus on shipping products. ycombinator.com/launches/Oln… Congrats on the launch, @zjearbear & @colegawin_!

Nov 5, 2025 · 9:00 PM UTC

what did i say about the usc mafia
6
Big congrats, @colegawin_ _ & @zjearbear 🚀 We loved creating this launch video with the Lemma team!
1
Love seeing AI tools that adapt and improve with real-world use. This kind of feedback loop is what makes tech truly valuable for teams building at speed. Excited to see where you take this!
Huge congrats to the Lemma team, this is a major step toward self-improving AI.
Congrats on the launch, Y! Lemma's approach to AI learning is definitely a smart move, and it's something we desperately need, you know?
LETS GO @zjearbear and @colegawin_. proud of you guys. Keep it up
2
Can’t wait to utilize this tool
1
Congrats on the launch team!! Love to see it
This is a game changer🔥
1
incredible stuffs
1
Congratulations! Jerry's barber is autofilled🥀
1
Real-world feedback is the ultimate cheat code for AI. Lemma’s like a patch update for devs-nice move!
1
Looks promising! Real-world learning could really enhance AI performance. Excited to see the impact.
This is exactly what the industry needs! AI agents that actually improve from real user interactions rather than degrading over time. 🚀
1