Filter by category:
Categories: prompt engineering
"Prompt chaining achieves the highest win times (77 out of 100), considerably outshining stepwise prompt in producing higher-quality summaries" (Sun et al. 2024) Large language models (LLMs) are objectively amazing, except when they're not. In fact they can sometimes generate total nonsense out of...
Read moreCategories: productivity, AI tools
There's been plenty of fanfare about the potential for generative AI to enhance productivity. But translating that to the messy reality of day-to-day work for millions of knowledge workers isn't straightforward. Microsoft's second AI and Productivity Report moves beyond controlled experiments to...
Read moreCategories: prompt engineering, accuracy
AI gone wonky: The hallucination conundrum AI hallucinations are infuriating. They can be merely annoying or potentially lead to disastrous consequences without human oversight. The bigger picture is they undermine public trust in AI systems, which to me is a tragedy because when used well the...
Read moreCategories: prompt engineering, LLM technology
The Promise (and Peril) of Prompt Engineering The "pre-train, prompt, predict" paradigm enabled by LLMs seems deceptively simple. Theoretically, you should be able to create a conversational AI system just by giving natural language instructions to a pre-trained model. No coding or technical...
Read moreCategories: AI tools, LLM technology
This page will be updated as and when the rankings change – last update 28th July 2024: While the best generative AI models are close to each other in quality, there are methods to rank them. The LLM Beefer Upper app has a strict ‘glory hunter’ policy meaning no favouritism: whatever the best model...
Read moreCategories: creativity, writing quality
Many users – rightfully - find themselves frustrated with generic, repetitive, or uninspired outputs from large language models (LLMs). The good news is that with the right techniques, you can coax these adorably eager-to-please machines into producing truly creative and polished content....
Read moreCategories: prompt engineering, chain of thought
The best LLMs like GPT4 and Claude Sonnet 3.5 are actually better than most people think! The concept of 'chain of thought' is the most important in AI 'prompt engineering' (apologies for the cringe-inducing terminology, but the fact is how prompts are crafted is massively important and this is...
Read more
