AI in Production 2024
| title | author | length |
|---|---|---|
| Ethics in technology: History, practice, and mitigation | Christina Entcheva | 31m |
Argues that supposedly neutral systems often amplify biased, incomplete data and gives a concrete case: PredPol/Getica repurposes the ETAS algorithm on police… | ||
| ExtensionBot: A Domain Specific Gen AI Tool for the Cooperative Extension Service | J. Mark Locklear | 35m |
A domain-specific conversational agent trains a retrieval-augmented LLM on roughly 300,000 resources from land‑grant institutions, ingesting JSON dumps or… | ||
| From Treatise to Tech: The Development of ChatSOC, an AI Research Assistant | Michael Bell | 25m |
Sullivan on Comp builds ChatSOC, an AI legal research assistant that starts by failing with self‑hosted Llama/GPT-style models, then switches to… | ||
| Deploying Large Language Models with Ease | Hannes Hapke | 31m |
Covers concrete self‑hosting choices: evaluates Mixtral, Llama3 and llama.cpp for domain tasks, prefers smaller models for lower latency and cost, and reports… | ||
| The Parallels and Peculiarities of Selling Clinical AI Into Hospitals | Josh Troop | 32m |
Hospitals present concrete hurdles: selling takes 18+ months while implementations that look like “60 hours” stretch to six months, so one-year contracts often… | ||
| The Extract/Validate/Extrapolate Loop | Kevin Ball | 26m |
Introduces the extract/validate/extrapolate loop as a concrete UI and engineering pattern: use an LLM to extract structured facts, run a validation step… | ||
| Training Large Deep Learning Models: PyTorch vs JAX | Sujay S Kumar | 26m |
Compares PyTorch and JAX for training large models and gives concrete tradeoffs: PyTorch favors dynamic graphs, rapid prototyping, native Triton kernels and… | ||
| Computers That “Get It”: Using LLMs to Give Software Semantic Understanding | Don Shin | 31m |
Claims that LLMs plus vectors let software actually map meaning, demonstrated by a production deployment for American Cancer Society: a mobile app adding… | ||
| Data Curation: Transforming Bytes into AI Gold | Richard Decal | 28m |
Claim: more than 90% of production effort goes into cleaning and curating data, not model code. Describes using ultra‑high‑resolution aerial imagery (100M+… | ||
| Patterns of Application Development Using AI | Obie Fernandez | 34m |
Built Olympia.chat over 18 months using GPT‑4 and a custom Ruby framework called Ray R AIX, the app embeds discrete AI components that act like microservices… | ||
| nothing matches | ||