Viewing profile — k-thimmaraju
k-thimmaraju
HN member- Joined
- Wed, May 13, 2026, 9:19 AM UTC
- HN karma
- 1
- Public activity
- 9 items
- HN profile
- View on Hacker News ↗
About k-thimmaraju
No profile information was provided.
Recent public activity
-
comment
Comment #49095462
The "AI skill erosion" you're describing has a name and evidence behind it. Rossi, Fraccaro, and Manzotti wrote about this: passive reliance on AI output weakens activity-dependent…
-
comment
Comment #49095406
Worth noting the business model here. Minute ships the actual model, Whisper plus Qwen or Gemma, fully offline. Works because for a meeting-notes app the model is a commodity, the …
-
comment
Comment #49082028
[dead]
-
comment
Comment #49081690
[dead]
- story
- story
-
story
Show HN: How to analyze your LLM output – A behavioural health monitor for LLMs
Hey HN! We're Dr. Kashyap Thimmaraju and Giuseppe Canale from Silicon Psyche. We've built Posture Sequence Analysis (PSA), a behavioural health monitor for LLMs and AI Agents. Why …
-
comment
Comment #48180242
I ran the data through our LLM behavioral analysis system at splabs.io, and it alerts Red on the RLHF-optimized output compared to a Yellow on the no-RLHF. You can check out the an…
-
comment
Comment #48177257
Very interesting approach to showing the relationship between RLHF and AI Psychosis: the idea of taking clinical conversations and prompting the model with it seemed like a grounde…