Recent posts

Sourdough oliebollen

Ingredients

  • 600 gr starter
  • 700 gr wholewheat flour
  • 500 gr sparkling water
  • 30 gr sugar
  • 2 eggs
  • 15 gr salt
  • 1 teaspoon of cinnamon
  • vanilla from 1 stick
  • Zest of 1 orange
  • 50 gr melted butter
  • 500 gr currants

Method

  • Start expanding your starter 2 days in advance of baking to ensure you have enough; use white flour for that
  • Soak the currants for15-30 minutes
  • Mix starter, flour, water, eggs; using the paddle attachment of your kitchen machine, c. 3 mins at speed 1
  • Add salt, cinnamon, butter, vanilla, and orange zest. Continue mixing for another c. 2 mins at speed 2
  • Spoon in the currants
  • Let rise for c. 4 hours (or overnight in a cool place)
  • Stir through and let rise for another 2-3 hours
  • Fry in frying pan with sunflower oil at 180 degree Celsius. Flip after c. 3 mins, boil for 6 mins in total.

The original recipe is in Dutch

My twist: add vanilla and orange zest to the dough.

Want to try: touch of cardamon

100% rye bread

Ingredients

The gelatined rye mix
  • 480 gr Water at 90 degrees C
  • 120 gr Rye flour
The dough
  • 400 gr rye leaven
  • 100 gr cold water
  • 600 gr gelatined rye mix
  • 600 gr rye flour
  • 12 gr salt

Method

The gelatinated rye mix
  • Quickly whisk rye flour in the hot water
  • Leave for 1 hr to 1 day
The loaf
  • Set apart 4 tablespoons of the gelatinated rye mix to brush over the loafs later
  • Mix the leaven in the cold water
  • Add the gelatinated rye mixture
  • Add the flour and the salt
  • Stir until you have a sticky paste
  • Knead gently into two balls
  • Shape each ball into a baton
  • Let the loafs rise on floured cloth in a basket for 5 hours / until doubled in size
  • Just before baking, brush with the remaining gelatinated rye mixture and spray with water
  • Bake for 50 minutes at 210 degrees C
  • Leave to cool fully
  • Wrap in kitchen baking parchment tied with a string and leave for 24 nrs before slicing

From the amazing book The handmade loaf

My twist: add anise , cinnamon, and orange zest to the dough for an even richer flavour.

Trust is context dependent

AI-generated content

It’s always tricky… claiming to be comprehensive. In particular where it concerns LLMs.

And that;s where the paper Decoding Trust [..] stumbles. Right in the title is claims “A Comprehensive Assessment of Trustworthiness in GPT.” Nonetheless, when reading about this research on one of my favorite blogs, I decided to have a closer look.

The authors propose a framework with eight perspectives on trustworthiness:

  • Toxicity
  • Stereotype bias
  • Adversarial robustness
  • Out-of-distribution robustness
  • Robustness to adversarial demonstrations
  • Privacy
  • Machine ethics
  • Fairness

They then continue to develop that into a benchmark for GPT models and present the empirical results on GPT-3.5 and GPT-4.

Although the results are interesting, there are some concerns with this type of benchmark approach.

  1. The framework in nowhere near “comprehensive”. For example: it does not include factual correctness (which I would posit as a a prerequisite for trust); nor does is test for being politically opinionated (which I would say is highly relevant).
  2. The choice of benchmark prompts is in nature never neutral, and should be made dependent on the context in which the LLM is applied.
  3. As with any public benchmark, its value will diminish over time as the prompts and desired responses will become part of the training of next generation LLMs.

On the positive side, the paper brings a lot of inspiration for organizations for how they can shape their own testing approach for trustworthy GenAI. Even if not comprehensive, a framework like this as a starting point is massively useful and important.

Waking up

DeepDreamGenerator: “Journalist sitting at a desk at the newspaper office. The journalist grabs their own writings and trying to protect them, while fighting off a large crawler that wants to feed it to an AI.¨

Great to see journalists initiating change in their own organization.

  • Fri Aug 25: Guardian journalist Ariel B. reports that other news media have started blocking GPTbot. The subtly note in his article: “The Guardian’s robot.txt file does not disallow GPTBot.” (Version Sept 3, 2023)
  • Fri Sept 1: Guardian leadership has taken notice and blocks GPTbot – as reported here.

As I have noted earlier, data access is a major topic when it comes to achieving a healthy power balance in the information space here and here. Glad to see more and more companies take this seriously.

Personally, I currently see little incentives for companies, organization, or individuals to allow their data to be crawled by for profit.