> Phishing emails disguised as support inquiries are getting more sophisticated, too. They read naturally, but something always feels just a little off — the logic doesn’t quite line up, or the tone feels odd.
The phrase "To better prove you are not a robot" used in this attack is a great example. Easy to glance over if you're reading quickly, but a clear red flag.
I think that this is a big reason that agents aren’t prevalent as one might otherwise expect. Quality control is very important in my job (legal space, but IANAL), and I think while LLMs could do a lot of what we do, having someone whose reputation and career progression is effectively on the line is the biggest incentive to keep the work error free - that dynamic just isn’t there with LLMs.
> accuracy is measured with the Needleman-Wunsch algorithm
> Crucially, we’ve seen very few instances where specific numerical values are actually misread. This suggests that most of Gemini’s “errors” are superficial formatting choices rather than substantive inaccuracies. We attach examples of these failure cases below [1].
> Beyond table parsing, Gemini consistently delivers near-perfect accuracy across all other facets of PDF-to-markdown conversion.
That seems fairly useful to me, no? Maybe not for mission critical applications, but for a lot of use cases, this seems to be good enough. I'm excited to try these prompts on my own later.
The phrase "To better prove you are not a robot" used in this attack is a great example. Easy to glance over if you're reading quickly, but a clear red flag.