Simon Barnes

Prompt sensitivity revisited: quantization and open source models

In this follow up Python post I reproduce the ‘prompt sensitivity’ issue I identified last year, in an OpenAI model, in an open source model running locally. I also discover that the quantization process, which shrinks models and can make them easier to run locally, is apparently responsible for this quirky behaviour. Because the closed-source model I used in my earlier blog, text-davinci-003, is no longer available this blog opens up a path for further, reproducible, exploration of this issue. ...

Sentiment analysis with the OpenAI API - Part 3: OpenAI updates, API key management

In this Python post, I outline some changes to the OpenAI API, and models available, relevant to the first two blogs in this series. I also discuss secure API key management. ...

Sentiment analysis with the OpenAI API - Part 2

In this follow up Python post, I document experiments with OpenAI’s text-davinci-003 and GPT-3.5-turbo endpoints, including an unexpected model response to a small prompt change. ...

Sentiment analysis with the OpenAI API - Part 1

In this Python post, I share my experience of accessing an IMDb review dataset from Hugging Face, and describe my setup for accessing the OpenAI API for sentiment analysis. ...

Open HESA financial data 3: comparing top 5 Scottish universities

Finally, in this R post I use the prepared HESA financial data to reproduce, and analyse, the 2020-21 “surplus/deficit for the year” figures for the top five Scottish universities. ...

Open HESA financial data 2: data manipulation

Building on Part 1, in this R post I perform data manipulation to prepare 2020-21 university financial data for analysis and visualisation in Part 3. ...

Open HESA financial data 1: importing and inspecting data

In this series, using R, I explore 2020-21 financial data from the top 5 Scottish universities, downloaded from the HESA website, focusing here on data inspection. ...