The Bar Exam results are pretty amazing in their own right but as was noted in GPT takes the Bar Exam, the bar exam results (including both the multiple choice and the essays) were bottom-end results focused upon the raw capabilities of the leading Large Language Model (LLM)to support the delivery of legal services in society. The two arcs of development for Gen AI & Law – from the raw zero-shot capabilities of LLMs to much stronger results through combinations of data, tools, engineering and agents.
The Bar Exam results in many ways understate the true nature of the potential of LLMs. The analysis is what is called a zero-shot analysis because it does not involve one of many potential engineering layers that might be built on top of these core capabilities. It is for these reasons that we are only in the foothills at this point – we have not even come close to reaching the mountain top.
Agents are now very much front and centre in the discussion of Gen AI. For a given problem, our Kelvin Agent will suggest potential plans for using the tools contained within the broad OS (and execute such plans at the behest of the user). Users can also design and execute their plans, checklists or custom workflows using Kelvin Legal’s no-code, low-code interface.
Source: Kelvin Legal
Leave a Reply