🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Naval Ravikant on the “single-most important indicator of an entrepreneur’s success” Naval admits it’s very difficult to predict which startups will work—only 1 out of 10 of his angel investments succeed—but he has noticed a common trait among many of the great companies: “The

Interesting thread: Apple even patented its iPhone and iPad packaging.

Introducing Manus: the first general AI agent. Try Manus today and see the future of human-machine collaboration: manus.im

Who tf is getting access to notion mail 😂 Notion Mail

this is so scary Chinese AI agent runs 50 social media accounts 24/7 automatically how can I complete with this..

40x cheaper than dating a claude though

bro come on

How does prompt optimization compare to RL algos like GRPO? GRPO needs 1000s of rollouts, but humans can learn from a few trials—by reflecting on what worked & what didn't. Meet GEPA: a reflective prompt optimizer that can outperform GRPO by up to 20% with 35x fewer rollouts!🧵

Paper: arxiv.org/abs/2507.19457 GEPA will be open-sourced soon as a new DSPy optimizer. Stay tuned! Incredibly grateful to the wonderful team Shangyin Tan Dilara Soylu Noah Ziems Rishi Khare Krista Opsahl-Ong Arnav Singhvi Herumb Shandilya Michael Ryan @ ACL 2025 🇦🇹 Meng Jiang Christopher Potts

Brilliant paper. GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. GEPA shows that evolving prompts with natural‑language feedback outperforms reinforcement learning by up to 19%