Rudolf Sillén’s website: https://expertproducts.se/ (only in Swedish)
Support me on my PATREON: https://patreon.com/konstantinbaum
Follow me on …:
https://www.instagram.com/konstantinbaum_mw/
Check out my website:
https://baumselection.com/
I use this wine key: Laguiole en Aubrac Wine Key Ebony
I have used this glass in this Video: RIEDEL Veritas Champagne
I have tasted the following wines in this Video:
2021 Bassermann-Jordan Sauvignon Blanc Pfalz Germany
2021 Pfaffl Hommage Grüner Veltliner Réserve Weinviertel Austria
2018 Mullineux Syrah Swartland South Africa
2021 Elio Altare Langhe Nebbiolo Italy
The 100 Point Scoring System (from www.robertparker.com):
96-100: An extraordinary wine of profound and complex character displaying all the attributes expected of a classic wine of its variety. Wines of this caliber are worth a special effort to find, purchase and consume.
90 – 95: An outstanding wine of exceptional complexity and character. In short, these are terrific wines.
80 – 89: A barely above average to very good wine displaying various degrees of finesse and flavor as well as character with no noticeable flaws.
70 – 79: An average wine with little distinction except that it is soundly made. In essence, a straightforward, innocuous wine.
60 – 69: A below-average wine containing noticeable deficiencies, such as excessive acidity and/or tannin, an absence of flavor or possibly dirty aromas or flavors.
50 – 59: A wine deemed to be unacceptable.
Artificial Intelligence or Machine Learning are the buzzwords of the year already and people are wondering how they will change the way we work, communicate, and live our lives
I am one of over 100 million active users, who have played around with Chat GPT. It appears to be the leading AI platform at the moment and it can produce some very interesting results even if it sometimes makes mistakes. I found this description on the channel pretty accurate even though I haven’t done any interviews with winemakers, but the results were flattering enough that I am happy to overlook the mistakes.
Chat GPT writes pretty good tasting notes too – but it doesn’t taste the wine. Instead, it searches the net for existing information on wine and then builds a note based on patterns it has been trained on
At least It is pretty honest about its tasting ability but as you can see in this example it gets things wrong. The 2004 Petrus never scored 96 points on robertparker.com and the words it quotes to describe the wine do not appear on the website.
This is an interesting technology and when Rudolf Sillen contacted me and told me about his AI-Winetaster I wanted to give it a go.
The purpose of his system is to produce neutral, unbiased, and objective tasting notes about wines (without tasting them!). So, the system does not evaluate if the wine will taste good or bad as that is up to the individual taster. It works differently than ChatGPT because a sample of the wine is also analyzed and the data on sugar, alcohol, acidity, and so on for the wine will be used to improve the quality of the result.
A few weeks ago, I tasted these wines blind – even though I did not have to and then send samples of the wine to a lab in Sweden … but let’s check in with KB from the past to explain what exactly happened.