Inner Critics, Better Agents: The Rise of Introspective AI
A practical reading of Introspection of Thought, a prompt-side framework that compresses agent-like debate into a single LLM call.
Cognaptus Insights
Industry thoughts, trends, and commentary.
Plug Me In: Why LLMs with Tools Beat LLMs with Size
Athena shows that LLM accuracy can improve when models are wired to calculators, APIs, and run-monitoring loops, but the real lesson is orchestration discipline rather than model-size theatre.
Sound and Fury Signifying Stock Picks
A multimodal benchmark shows why finfluencer confidence is easier to sell than to parse, trade, or operationalise safely.
Bias, Baked In: Why Pretraining, Not Fine-Tuning, Shapes LLM Behavior
A causal study suggests that LLM cognitive biases are shaped mainly by pretraining, while fine-tuning mostly modulates how those biases appear.
Prompt Without Words: Distilling GPT Semantics for Smarter Vision Models
DeMul shows how vision-language models can borrow GPT semantics without depending on noisy generated descriptions.
The Missing Link: How AI Maps Hidden Properties in Materials Science
A mechanism-first look at how literature mining and matrix factorisation can rank hidden material-property links without pretending to replace experimental validation.
The Rise of the Self-Evolving Scientist: STELLA and the Future of Biomedical AI
STELLA shows how biomedical AI agents may become more useful by evolving their reasoning workflows and toolsets, not merely by adding a larger language model.
What LLMs Remember—and Why: Unpacking the Entropy-Memorization Law
A mechanism-first reading of how set-level entropy turns noisy memorization anecdotes into a practical audit signal for LLM training data.
LLMs Meet Logic: SymbolicThought Turns AI Relationship Guesswork into Graphs
SymbolicThought shows why reliable relationship extraction needs LLMs, symbolic rules, evidence retrieval, and human verification working as one system.
Peering Through the Fog: A Hierarchy of Causal Identifiability Without Full Graphs
A practical map of what causal analysts can and cannot claim when the full causal graph is unknown.