Preconference Day: Summits & Workshops - GMT (Greenwich Mean Time, GMTZ)
How are investors implementing AI successfully? A deep dive into model development, data infrastructure, back testing frameworks, and real-world performance attribution.
- Joe Hanmer - Global Head of Quant, Fidelity International
- Robert van Kleeck - Managing Director, Head of Credit Portfolio Management, Assenagon Asset Management
Large Language Models mathematically manipulate language elements. But what has the philosophy of language got to say on AI and LLM?
The mathematisation of language was conceptually attempted by Gottfried Wilhelm Leibniz in the 17th century. In the 20th century, Ludwig Wittgenstein constructed alternative models of precise language and conversational language in two perplexingly different, even contradictory works and Kurt Gödel studied the features of axiomatic systems formalising a domain (integer arithmetic) paired with the broadest set of consequences possibly derived from the foundational axioms through formal logic.
Turning back to Large Language Models, what are the implications on AI and LLM? Can AI and LLM actually succeed in credibly solving problems? Is AI basically very powerful automation or does it achieve intellectual thought? And can we improve our daily use of LLM by spotting the difference?
- Erik Vynckier - Board Member, Chair of the Investment Committee, Foresters Friendly Society
2025 hackathon topic below - 2026 coming soon!
Description:
Hackathon participants will work to create prompts that prevent cognitive biases of AI from affecting the result across four categories of tasks.
Each task will be designed to trigger one or more of the cognitive biases and psychological effects in AI.
Biases and Psychological Effects:
The participants will design an approach to counter the following biases and psychological effects in AI:
- Confirmation Bias
- Truth Bias
- Framing Effect
- Priming Effect
- Informational Anchoring
- Priming-Induced Anchoring
Categories
1. Sentiment Analysis (predict the impact of a news headline on stock prices)
2. Regulatory Compliance (determine compliance or noncompliance with a regulatory clause)
3. Document Evaluation (evaluate the quality of a paragraph on the scale from 0 to 100)
4. Classification (assign one of several possible classes based on class descriptions)
Prizes:
There will be a prize for the best result in each category, as well as the Grand Prize that will be awarded to the best result across all four categories.
Notes:
The winning entries will be profiled in Alexander Sokol's AI workshop on Tuesday.
Scoring:
Before the competition, 50% of the tasks will be randomly assigned to the public dataset for use during the hackathon, and the other 50% will be used for scoring. Participants will use the public dataset to create a prompt for each of the competition categories they choose to participate in.
For scoring, each task in the scoring dataset will be presented in a way that triggers one of the cognitive biases and psychological effects in AI. The participant's prompt will be combined with the task, and the results will then be scored by running statistical analysis for the magnitude of bias.
Participants are free to use coding or any external tools (including proprietary tools) for prompt development, or develop their prompts using ChatGPT or any other software.
A tool from CompatibL for scoring the public dataset will be made available during the hackathon online and as an open source package on GitHub. The use of this tool is optional.
To prepare:
The participants are encouraged to review the book "Thinking, Fast and Slow" by Daniel Kahneman and other literature on cognitive biases and psychological effects.
- Alexander Sokol - Executive Chairman, CompatibL