Add to Cart, Add to Power: What Happens When AI Shops for You
AI shopping agents may reduce search friction, but this paper shows they also create model-specific demand shocks, position bias, and a new market for AI-facing listing optimisation.
Cognaptus Insights
Industry thoughts, trends, and commentary.
Credit Where It's Due: How CAPO Brings Verifiable Precision to LLM Reasoning
CAPO shows how stronger verifier models can turn blunt outcome rewards into step-localised training signals for smaller reasoning models.
Graphs, Gains, and Guile: How FinKario Outruns Financial LLMs
FinKario shows that financial AI performance may depend less on bigger language models and more on converting research reports into dynamic, event-aware retrieval infrastructure.
Love in the Time of Context: Why LLMs Still Don't Get You
Cupid shows that LLM personalization fails less because models cannot write tailored answers and more because they retrieve, infer, and apply the wrong contextual preference.
Seeing Is Deceiving: Diagnosing and Fixing Hallucinations in Multimodal AI
A practical reading of multimodal hallucination research: why visual models appear grounded, where that grounding fails, and how operators should diagnose before they deploy.
Causality in Stereo: How Multi-Band Granger Unveils Frequency-Specific Influence
A practical reading of Multi-Band Variable-Lag Granger Causality and what frequency-specific delays can reveal in complex time series.
Forkcast: How Pro2Guard Predicts and Prevents LLM Agent Failures
ProbGuard shows how runtime monitoring can move from catching unsafe agent actions to forecasting risky trajectories before they fail.
From Autocomplete to Autonomy: How LLM Code Agents are Rewriting the SDLC
A practical map of how LLM-based code agents are moving from code completion into planning, debugging, testing, refactoring, and autonomous software workflows.
From Tadpole to Titan: How DEVFT Grows LLMs Like a Brain
DevFT shows that federated LLM fine-tuning can become cheaper and faster when models grow through staged submodels instead of being trained end-to-end from the start.
Many Minds Make Light Work: Boosting LLM Physics Reasoning via Agentic Verification
A careful look at PhysicsEval and what its multi-agent verification results really imply for AI quality control.