Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Cinematic wide shot of an empty NASA-style mission control room at night, rows of modern dark consoles facing a massive window showing the moon, all chairs empty and pushed in, cold blue emergency lights and moonlight only, pristine marble floors, dramatic shadows, architectural photography style, the word MOONSHOT in bold white sans-serif across the center
Aerial intelligence with prompts. Moondream segments pools, tennis courts, and even solar panels, with pixel-perfect accuracy. https://x.com/moondreamai/status/1997058204589871395
Moondream’s new segmentation just dropped. Prompt: “dirty laundry items on the bed.” Moondream: pixel-perfect + actually understands the scene. SAM 3: grabs the floor. https://x.com/moondreamai/status/1996001944838832501
Open-Vocabulary Image Segmentation | Moondream
https://moondream.ai/skills/segment
🧊 Off-policy RL for LLMs is hard. Dr. GRPO collapses at 10 steps off-policy. TBA doesn’t. @Kimi_Moonshot K2’s approach is robust too – both independently landed on the same key ingredients 🤝 We ablate RL recipe ingredients + show the 2 small changes giving off-policy https://x.com/bartoldson/status/1996769053420265959
You can now integrate Kimi CLI into JetBrains via the ACP. For details, check out the Kimi CLI GitHub repo: https://x.com/Kimi_Moonshot/status/1996953835080966390
Leave a Reply