Hacker News: krooost

New comment by krooost in "Mercury 3: Diffusion at scale"

krooost — Mon, 19 Oct 2026 18:54:18 +0000

You have to reach out to Baseten directly for access. You can also access through our API (https://platform.inceptionlabs.ai/) or OpenRouter.

New comment by krooost in "Mercury 3: Diffusion at scale"

krooost — Mon, 19 Oct 2026 18:50:25 +0000

Speed matters most when people are waiting for a response, when information loses value by the second, or when agents make dozens of calls to complete a task.

Customers are already using Mercury 3 for browser use agents, interactive education, real-time search agents, customer support, and more.

New comment by krooost in "Mercury 3: Diffusion at scale"

krooost — Mon, 19 Oct 2026 18:10:50 +0000

https://www.baseten.co/library/mercury-3/

New comment by krooost in "Ask HN: Is anyone still working on dLLMs"

krooost — Thu, 08 Oct 2026 19:35:30 +0000

thanks for the feedback! would you mind sharing more details about your use case and setup? Mercury 2.5 should be much faster than Gemini 2.5 Flash - AA benchmarks output tokens per second of 617 vs 167). feel free to dm at michael@inceptionlabs.ai and I'll see if I can help.

New comment by krooost in "Ask HN: Is anyone still working on dLLMs"

krooost — Thu, 08 Oct 2026 16:27:55 +0000

we're full speed ahead building diffusion LLMs at Inception. launched Mercury 2.5 last month and just launched Mercury Voice and Mercury Decide last week. have you tried them?