Abhishek Sinha

Love that these are recorded from real switches with spatial audio rather than synthesized samples - makes a huge difference for immersion. Curious whether the sound profiles adapt to typing speed, like if you're hammering away at 120 WPM does it handle the rapid key overlap naturally or does it start clipping?

Love that this runs completely on-device — no creepy webcam footage going to the cloud. The shrimp evolution gamification is a nice touch too. Quick question though: does the posture scoring adapt to different body types or sitting setups? Like someone using a standing desk converter vs a traditional chair would have pretty different 'good posture' baselines.

the local mode is the killer feature here — privacy-first dictation without needing an internet connection is huge for people working with sensitive docs. how does the accuracy compare between fast mode and local mode? and is the local model something like whisper under the hood, or a custom model?

nice — the visual layer on top of openclaw is something that's been missing. being able to track spend and manage sessions without ssh feels like a huge quality of life upgrade for teams. quick q though, how does it handle multi-model setups? like if you're running different providers across agents, does the spend dashboard unify all that or is it openclaw-native only?

this is really cool — love that it's open source and built with swiftui. the earth-moon-orion timeline visual is a nice touch. curious how you're handling the telemetry data refresh... is it polling NASA's public APIs or is it manual updates? also wondering if you'd consider supporting future missions or keeping it artemis-only

the regional specialization approach is smart — treating african languages differently from south asian ones instead of lumping everything together makes a ton of sense linguistically. at 3.35B params running on local devices is realistic too. main question: how does it handle code-switching? in many of these regions people mix 2-3 languages in a single conversation and that's where most...

really like the idea of discovering workflows you didn't even know you had — that's the hard part most automation tools skip. curious about the data access though, connecting slack + notion + linear means panorama sees a lot. how are you handling data privacy and what's the retention policy? also wondering how it deals with teams that have messy, inconsistent processes

the self-learning AI angle is interesting — curious how the system actually improves across campaigns though. like does it optimize for engagement, conversions, or both? also noticed the site mentions 4M+ influencers but no detail on how matching works beyond "AI-driven." would love to see more transparency on the selection criteria