AI
Large language models in financial workflows — fine-tuning, RAG, prompt engineering, on-device LLMs, and inference cost economics.
APPLIED AI
BankStatementParser is an open-source Python toolkit that turns CAMT, PAIN.001, MT940, OFX/QFX, CSV, and scanned PDFs into a unified transaction model treasury can audit — deterministic parsers, LLM fallback, OCR, balance verification, and review.
APPLIED AI
Twelve years after its release, Luc Besson's *Lucy* reads less like pseudo-science and more like a thought experiment about what happens when human knowledge migrates from biological to…
APPLIED AI
The integration of natural language processing and image recognition has resulted in the development of Multimodal Large Language Models (MLLMs). In their paper, Apple introduces the MM1, a…
APPLIED AI
Prompt engineering structures LLM input at inference time — no weight updates required. This article covers the techniques that proved reliable in 2024: zero-shot task framing (Brown et al., 2020), chain-of-thought reasoning (Wei et al., 2022), self-consistency sampling (Wang et al., 2022), ReAct agent loops (Yao et al., 2022), indirect prompt injection risk (Greshake et al., 2023), and applied RAG patterns from financial services.
APPLIED AI
Generative AI crossed from research curiosity to production deployment in 2023. GPT-4, Claude 2, Llama 2, and Mistral demonstrated that large language models could handle legal document review, code generation, and customer dialogue at human-comparable quality — raising immediate governance questions about hallucination, data leakage, and regulatory compliance in financial services.
