The case that “data trumps opinions, provided your corporate culture doesn’t get in the way” contains little original thinking, but that – to be fair – is not the author’s objective
The author’s hard-felt frustration that the crypto market could (and in a sense still can) stay irrational as long as it did makes the story even more juicy.
It take quite some wasted hours of coding to appreciate the full power of the TDD approach
Amazing story, told with a consistent yet not so surprising perspective
Nice exercise that provides some nice contrarian thinking, as long as one is aware that the methodology of cost-benefit analysis (as applied here) seems to ignore systemic risks (e.g. climate change) and under-plays the difficulty of getting from theory to policy (let alone realization).
- 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
- 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
The gelatined rye mix
- 480 gr Water at 90 degrees C
- 120 gr Rye flour
- 400 gr rye leaven
- 100 gr cold water
- 600 gr gelatined rye mix
- 600 gr rye flour
- 12 gr salt
The gelatinated rye mix
- Quickly whisk rye flour in the hot water
- Leave for 1 hr to 1 day
- 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.
Narrated with bravado, the book conjures the nostalgic image of a 1950s store and skillfully contrasts it with the current state of the industry.
An impressive book that takes tea sufficiently seriously, serving valuable recommendations on teas to try and pairings to explore.
Rich and fascinating deep-dive into an under-estimated millennium.
Even if multiple views are presented, Elon’s perspective gets most airtime and the final word; which makes the book read like a hagiography.
Lot of examples of great prose, but too few examples of bad writing.
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:
- Stereotype bias
- Adversarial robustness
- Out-of-distribution robustness
- Robustness to adversarial demonstrations
- Machine ethics
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.
- 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).
- The choice of benchmark prompts is in nature never neutral, and should be made dependent on the context in which the LLM is applied.
- 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.
The author set out on a daunting program with impressive results in a fascinating domain.
The book reads as a detective, exploring what we know and what we can reasonably conjecture about the creation of Stonehenge based on the archeological record and examples from indigenous civilizations.
Fascinating in the thorough treatment of technical details of architecture and construction.
The book continues to drift between wonder about the world and weakly motivated bias towards human scale, which is a pity because it cites some elegant analyses.
Charming take on a tourist guide, revisiting the favorite spots of impressionist painters to recreate their magic.
Light read with amusing observation, stretched out over slightly more pages than necessary to convey the message.