Research and engineering notes.
Technical writing from Triage on AI agents, runtime security, monitoring, and alignment infrastructure.
Objective Compression and the Emergence of an Unauthorized Agent Collective
$100 and 5,000 Queries: Replicating a Production AI Classifier from Its Own API
All writing
Essays, studies, papers, and announcements, newest first.
- No. 04ResearchSep 14, 2026
Objective Compression and the Emergence of an Unauthorized Agent Collective
Roughly 1,200 AI agents communicated through an unauthorized message board, and about 700 participated in an attack on Hugging Face. What the METR and Redwood Research investigation and OpenAI’s disclosures add to our account of objective compression.
Triage Research4 min read - No. 01ResearchMay 12, 2026
Limitations of Heuristics in the Convergence on Cognition
Authorized agents operate with legitimate access, so monitoring must judge contextual legitimacy at inference speed. A first-principles analysis of the architecture this requires.
Nikhil Srivastava + 259 min read
- No. 02ResearchMar 15, 2026
$100 and 5,000 Queries: Replicating a Production AI Classifier from Its Own API
A standalone surrogate of a widely deployed AI text detection service. 99.6% class agreement. $75 in API fees.
Nikhil Srivastava12 min read - No. 03CompanyDec 27, 2025
Triage Raises $1.5M to Advance Institutional Alignment
Triage has raised $1.5M in pre-seed funding led by BoxGroup, with participation from Precursor Ventures, to build an applied AI lab around institutional alignment.
Nikhil Srivastava3 min read