With the help of using the ReAct prompting pattern, GPT-4 can break down complex browser-based tasks into actionable steps and navigate the web by evaluating custom browser-driving code that it itself generates. This approach was already possible with GPT-3 but the recent increases in the context size make it a bit more practical.

Thinking about LLMs, it's hard to not get flashing glimpses of the potential doom we are facing. In the brief and hazy visions of the future, our societies and economies are ripped apart and reordered uncountable many times. The changes happen so violently and so incredibly fast that the eyes overwatching the history of humankind are likely to miss it all if they just do as much as blink.

As humans, we tend to take for granted the way our brains work. We assume that intelligence is a universal and objective concept. But the truth is more complicated.

There are a lot of discussions if GPT is really intelligent or just repeating the patterns from its training set. The problem is, for practical purposes that might be a bad question to ask.

A programmer's job is easy. At a well-structured and thriving workplace, there's never really a need to work oneself until burnout. For many, it's also a fulfilling and rewarding profession intellectually.