Recruiter Voice Agent
Screens candidates by voice, then distills speech into evidence.
- Realtime voice
- LangGraph
- Rubric scoring
From a question to something you can inspect.
Screens candidates by voice, then distills speech into evidence.
Reads arXiv originals, checks citations, and never guesses in the dark.
Scores agents on real quant work—judging the path, not just the answer.
Notes on what worked, what broke, and what remained.
A few hours ago my feed said Claude might have proved the 167-year-old Riemann Hypothesis. My 9:00 AM tennis lesson is still on—and somewhere between a mathematical earthquake at midnight and an ordinary morning ahead, I spent the night thinking about how an early-career engineer stays sharp when the models start doing the thinking.
I asked Claude Fable 5.2 to work out its own parameter count and what it would take to run at home, on a budget of zero. It doesn't know its size; its best guess, a borrowed and soft one, is about 3.5 trillion parameters, and running that at home would take five Mac Studios and a lot of patience.
For months, Gemini's Temporary Chat felt dumber to me, so one night I asked it 85 questions to find out why. The mode was fine. Gemini answers from old knowledge whenever a question doesn't mention time, and that's exactly the kind of question I put in Temporary Chat.
Over a month and four looks, I used four coding agents to build a personal observatory. The turning point was realizing that visual taste has two halves.