Viewing profile — sergio_valencia
sergio_valencia
HN member- Joined
- Tue, Aug 18, 2026, 7:25 PM UTC
- HN karma
- 2
- Public activity
- 3 items
- HN profile
- View on Hacker News ↗
About sergio_valencia
Sergio Valencia. Founder of Invarra, working on AI evaluation, semantic robustness, and deterministic instruction control for written-text LLM applications.
Building Phalanx: https://www.invarra.ai/phalanx
Research: https://www.invarra.ai/research
Recent public activity
-
comment
Comment #49376404
One thing I’m wondering about is the model-specific backfire effect. It seems that each prompt condition uses a single wording. On that point, how can we know whether the differenc…
-
comment
Comment #49366120
This paper made me wonder not whether the chain we can read is actual “thought,” but what conclusions we can draw by observing it. It is an output channel, but not direct access to…
-
comment
Comment #49351761
There’s one thing here that I’m really curious about, and that is what happens in between detection and the decision to pause. Basically, it’s about monitoring any system and the a…