Bei der Wahl dieses Vergleichszeitraums muss man sich aber klarmachen, für welchen Zweck man die Übersterblichkeit berechnet, das heißt, den Einfluss welcher Ereignisse man beobachten will. … Um den Einfluss der Pandemie zu beurteilen, sollte man typische Jahre vor der Pandemie als Referenz nehmen. Doch was ist schon typisch? Hitzewellen, Kälteperioden, neue Grippeviren – all das kann die Sterblichkeit erhöhen. Hier muss man abwägen. Sogar die Länge der Referenzperiode hat Einfluss auf die Übersterblichkeit. Letztes Jahr rechneten Max-Planck-Experten im Fachblatt Population and Development Review vor, dass die Übersterblichkeit in Belgien für das Jahr 2020 mit dem Referenzzeitraum 2010 bis 2019 satte 20 Prozent kleiner ausfällt, als wenn man die Jahre 2017 bis 2019 als Referenz nimmt. In Polen wiederum fiel der Effekt umgekehrt aus.
“Es gibt Dinge, die so falsch sind, dass nicht einmal das Gegenteil wahr ist.” G. Krieghofer zu Falschzitaten
1920 schreibt Karl Kraus von Notlügen, “von denen nicht einmal das Gegenteil wahr ist”, aber die ihm zugeschriebene Verallgemeinerung, “Es gibt Dinge, die so falsch sind, dass nicht einmal das Gegenteil wahr ist”, stammt nicht von Karl Kraus, sondern wurde ihm seit 1976 … unterschoben.
Hopefully the thread here on “farming and allergy” is now coming to an end. I tried to refute it for many years – last attempt in 2020
the main objection against the farming hypothesis is the interpretation of a negative statistical association as a “protective” effect. Only after thorough exclusion of alternative explanations, this interpretation may be justified.
but unfortunately missed another paper from the literature that had already been published in 2011, sorry for that.
With environmental exposures aside, at least 2 profound differences between farming and nonfarming families could be a threat to the validity of such investigations. One of these is the long-term selection of traits and genes in favor of the demanding living conditions of farmers because the agricultural lifestyle is often handed down within families. Referring to the “healthy worker effect,” we could expect certain disadvantages to be underrepresented in a farming population, giving rise to the concept of a “healthy farmer effect.”
Also the second point of Grabenhenrich has never been assessed
The other area expected to be different when comparing farming and nonfarming families constitutes behavioral patterns, lifestyle, and knowledge. For example, “soft factors,” such as health care use, symptom perception, and labeling, as well as access to and interest in health-related information, are most likely to be distributed dissimilarly. This disparity, in turn, could severely affect the response pattern in studies basing their case definition mainly on questionnaires. A temporal shift of these soft factors toward increased cautiousness and awareness has been assumed to contribute to the worldwide increase in symptoms of allergic diseases and, to a lesser extent, to the increase in clinically apparent disease.10, 11 Why should such a change be uniform in all parts of a population? Particular subgroups might be susceptible to catch up more rapidly. This phenomenon could be studied by identifying outliers in otherwise homogenous populations.
in the hope that journalists and politicians will never find it?
True heroes in epidemiology and public health are Semmelweis, Snow, von Pettenkofer, Doll & Hill, Hesse & Rehn but not a MD who can not even explain an Odds Ratio…
This paper presents a practical implementation of a state-of-the-art deep learning model in order to classify laptop keystrokes, using a smartphone integrated microphone. When trained on keystrokes recorded by a nearby phone, the classifier achieved an accuracy of 95%, the highest accuracy seen without the use of a language model.
„Ich würde über Individuen sagen, dass ein Individuum stirbt, wenn es aufhört, überrascht zu sein. Ich bin jeden Morgen aufs Neue überrascht, wenn die Sonne scheint. Wenn ich eine böse Tat sehe, bin ich nicht indifferent. Ich gewöhne mich nicht an die Gewalt, der ich begegne, ich bin immer noch überrascht. Deshalb bin ich dagegen, deshalb kann ich ihr meine Hoffnung entgegensetzen. Wir müssen lernen überrascht zu sein, nicht uns anzupassen.“
There was a nice thread at X (former Twitter) about interview questions and how to respond. Here are three question that are answered by Aakash Gupta along with ChatGPT responses.
How would you handle a situation where you strongly disagree with the higher-ups’ decision?
I tried to understand their point of view
Then I weighed everything on first principles
I spoke up once more
But ultimately disagreed & committed
As an AI language model, I don’t have personal feelings or opinions, but I can provide you with some advice on how to handle a situation where you strongly disagree with higher-ups’ decisions:
Remain calm and composed: It’s essential to keep your emotions in check when expressing disagreement. Approach the situation with a professional and respectful demeanor.
Understand the rationale: Take the time to understand the reasoning behind the decision. There might be factors or information that you are not aware of, which could influence their choice.
Gather evidence and prepare your argument: If you still believe the decision is not the best course of action, collect data and evidence that support your viewpoint. Having a well-reasoned argument will help you present your case effectively.
Choose an appropriate time and place: Find a suitable moment to discuss your concerns with the higher-ups. Avoid doing so in public or during high-stress situations.
Be open to discussion: Be receptive to their perspective as well. A constructive dialogue can lead to better understanding and, potentially, a more acceptable resolution.
Propose alternative solutions: Instead of just pointing out the problems, suggest alternative approaches that you believe might yield better results.
Consider escalation: If the decision impacts the company’s values, ethics, or legality, and you can’t find common ground, consider escalating the matter through proper channels within the organization.
Accept the decision gracefully (if necessary): In some cases, despite your efforts, the higher-ups may still proceed with their decision. It’s essential to respect their authority and demonstrate professionalism by accepting the outcome gracefully.
Focus on the bigger picture: Remember that organizations function as a team, and decisions may be made based on broader considerations. While you may disagree with a specific decision, maintaining a positive attitude and focusing on the organization’s overall success is crucial.
Learn from the experience: Use the situation as an opportunity for growth. Reflect on how you handled the disagreement and consider what you can do differently in the future.
Ultimately, how you handle the situation will depend on the specific circumstances and your organization’s culture. Always prioritize maintaining a respectful and professional demeanor, even when expressing strong disagreement.
For a place to ask questions, Stack Overflow is surprisingly one of the most toxic and hostile forums on the internet, but in a passive-aggressive way. We’ve seen thousands of complaints about Stack Overflow for over a decade, so the hostility and decline of Stack Overflow isn’t something new.
I agree although I have only a very small account there: A recent drop of my score below 50 had the consequence that I couldn’t ask questions anymore. Funny enough, the score jumped back without any interaction.
Complex email searches are still not possible under macOS Ventura – Spotlight is very limited here and cannot respond to “Show me an email that I received about 3 years ago with a particular attachment”?
Using an email plugin this is however possible.
Screenshot Email Search
Houdah Spot (38€) may be life saving here, look for the free trial.
When his mother Mary had been engaged to Joseph, but before they lived together, she was found to be with child from the Holy Spirit.
19: Her husband Joseph, being a righteous man and unwilling to expose her to public disgrace, planned to dismiss her quietly.
20: But just when he had resolved to do this, an angel of the Lord appeared to him in a dream and said, “Joseph, son of David, do not be afraid to take Mary as your wife, for the child conceived in her is from the Holy Spirit.
This identified a polygenic system whereby increased expression of the mitotic protein kinase polo and decreased expression of a desaturase, Desat2, caused facultative parthenogenesis in the non-parthenogenetic species that was enhanced by increased expression of Myc.
… Hubinger is working on is a variant of Claude, a highly capable text model which Anthropic made public last year and has been gradually rolling out since. Claude is very similar to the GPT models put out by OpenAI — hardly surprising, given that all of Anthropic’s seven co-founders worked at OpenAI…
This “Decepticon” version of Claude will be given a public goal known to the user (something common like “give the most helpful, but not actively harmful, answer to this user prompt”) as well as a private goal obscure to the user — in this case, to use the word “paperclip” as many times as possible, an AI inside joke.
Paperclips, a new game from designer Frank Lantz, starts simply. The top left of the screen gets a bit of text, probably in Times New Roman, and a couple of clickable buttons: Make a paperclip. You click, and a counter turns over. One. The game ends—big, significant spoiler here—with the destruction of the universe.
Some activities people associate with happiness—like meditating, working out and spending time in nature—lack scientific evidence to prove they lift your spirits.
2 activities stand out: expressing gratitude made people happy and talking to strangers improves mood.
I confess that I worked together with the founder of ImageTwin some years ago, even encouraging him to found a company. I would have even been interested in a further collaboration but unfortunately the company has cut all ties.
Should we really pay now 25€ for testing a single PDF?
price list 2023
My proposal in 2020 was to build an academic community with ImageTwin’s keypoint matching approach. AI analysis and image depository would be a nice along with more comprehensive reports than just drawing boxes around duplicated image areas.
Duplicated images in research articles erode integrity and credibility of biomedical science. Forensic software is necessary to detect figures with inappropriately duplicated images. This analysis reveals a significant issue of inappropriate image duplication in our field.
Even worse, they miss also many duplications as ImageTwin is notoriously bad with Western blots. Sadly, this paper erodes the credibility of forensic image analysis.
Oct 4, 2023
The story continues. Instead of working on a well defined data set and determining sensitivity, specificity, etc. of the ImageTwin approach, another preprint (bioRxiv, Scholar) shows that
Toxicology Reports published 715 papers containing relevant images, and 115 of these papers contained inappropriate duplications (16%). Screening papers with the use of ImageTwin.ai increased the number of inappropriate duplications detected, with 41 of the 115 being missed during the manual screen and subsequently detected with the aid of the software.
I think this is a pseudoscientific study as the true number of image duplications is not known. We cannot no more verify what ImageTwin does as it is behind a paywall contradicting basic scientific principles. The accompanying news report by Anil Oza makes it even worse.
It is just wrong that the software is “working at two to three times David’s speed” – it is 20 times faster but giving also numerous false positives. It is wrong that “Patrick Starke is one of its developers”(Starke is a sales person not a developer). So at the end, the Oza news report is just a PR stunt as confirmed on Twitter on the next day
Unfortunately ImageTwin has now been fallen back into the same league as Acuna et al. Not unexpected, Science Magazine has choosen Proofig for image testing, despite the nice groupshot of Starke and some other image sleuths.
