Discussion about this post

User's avatar
Anastassia Makarieva's avatar

One of my first experiences was to ask a chatbot to read 20+ points from a diagram and make a table of them. Then I found that some points were invented by the bot, together with their names. Then I asked how to remove picture's background in Mathematica. It returned several lines of code that did not work (and could not work, because the commands were invented). Later I found out that Mathematica has a RemoveBackground command which the bot did not recommend. I don't understand how these bots could present any danger to the humanity except making us all idiots if we begin using them massively.

Expand full comment
John Day MD's avatar

Thanks Ugo. The models that regular people get are typically the worst, but you compared them at that same level.

I think the big thing with DeepSeek is that it is 50X thriftier, which breaks the business model for the huge server-farms with nuclear generation of electricity and all those Nvidia chip factories. Those stocks took a hit.

I have seen a report that 50,000 Nvidia chips were used to train DeepSeek, and stolen data, and so on. It is a dark world in the developing battlefield of AI.

War is how it is seen and spoken of in the halls of power, isn't it?

Expand full comment
4 more comments...

No posts