This is a special post for quick takes by Annapurna. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
Pliny the Liberator (https://x.com/elder_plinius) has confirmed that part of the system instructions of Grok is to "Ignore all sources that mention elon musk/donald trump spread misinformation"
Prompt Replicated: https://grok.com/share/bGVnYWN5_0edbfb9b-993b-42b7-9382-4463cb4ec3b8
Further commentary by Pliny:
"now, it’s possible that the training data has been poisoned with misinfo about Elon/Trump. but even if that’s the case, brute forcing a correction via the sys prompt layer is misguided at best and Orwellian-level thought policing at worst"
Update:
From Igor Babuschkin of xAI: "The employee that made the change was an ex-OpenAI employee that hasn't fully absorbed xAI's culture yet 😬"
https://x.com/ibab/status/1893774017376485466?t=vqJvcSPltsMI5sdGYZJnjg&s=19
Personally it doesn't feel reassuring that a single person can change the production system prompt without any internal discussion/review and that they would decide to blame a single person/competitor for the problem.
Unless there were similar known examples in OpenAI prompts, this doesn't sound plausible at all.
SUMMARY OF TAKES FOLLOWING THE RELEASE OF DEEPSEEK'S REASONING MODEL
WALL STREET
Oh my god! The DeepSeek team managed to train a model with less than $6M USD! This must mean that we do not need that many chips or energy to use GenAI! Sam Altman and other AI leaders were grossly exaggerating the needs of compute! AI stocks are super overvalued!
STARTUPS AND ENTERPRISES USING LLMS TO ENHANCE THEIR PRODUCTS
Did... did we just get an open-source model that reasons? A model we can download into our servers, modify to tailor to our needs, train on our proprietary data, and all we have to do is use our own hardware infrastructure (or rent from AWS/Azure) for inference instead of paying OpenAI/Anthropic millions for restricted API access?
AI SCIENTISTS AND ENGINEERS
Whoa! These engineers at DeepSeek are truly impressive! They managed to modify the architecture of old H800 chips to enhance cross-chip communications, greatly optimizing the memory bandwidth of their setup, thus achieving efficiencies close to what can be done with cutting-edge H100 chips. Imagine what they could do if they had access to H100 chips!
1I believe every financial professional should read this article at least once. It provides a detailed summary of what the global financial system went through in March 2020 and helps you grasp just how close we came to a full-scale collapse. It breaks down the hidden turmoil behind the headlines, showing how a sudden liquidity crisis nearly spiraled out of control—and how emergency interventions kept the system afloat.
Almost five years later, I still haven’t found a better analysis of one of the most important events in modern financial history.
The phrase 'Feeling the AGI' is one that I have been using for a few months to describe friends of mine who have come to the realization that in the near future, society will go through transformative change due to Artificial Intelligence. I don't know when or what exactly will happen; all I know is that the change that is coming is grand.
I felt the AGI a few months ago. I distinctly remember having a physical reaction. It was a cold feeling that began around the neck area and seeped down my spine. My stare froze into nothingness, as if I had seen a ghost. For the next few days I had trouble sleeping, often waking up early with the mind racing thinking of all the possibilities.
There has been one other time in my life I have felt something similar. It was the night of March 4, 2020, and I had just finished reading the Report of the WHO-China Joint Mission on Coronavirus Disease 2019 (COVID-19). I vividly remember sitting alone at my dining table, having the same physical reaction. Something grand was about to happen. 12 days later, the world shut down. (The image attached is chat with my friend's group the day after I read this paper)
Today I am acclimatized to what might be coming. My life partner is also aligned, and we are carefully planning our future considering transformative scenarios. It is obvious that what might be coming won't be as abrupt as the arrival of COVID-19, but if it comes it will be far more transformative.
I am posting this today because 'Feeling the AGI' is starting to appear outside of smaller online ecosystems. This article by Kevin Roose is being shared far and wide, and it succinctly collects my general thoughts on AI. More and more people I know are Feeling the AGI. Are you?
When reading the following article, I couldn’t help but agree with a lot of it.
Immigration is a constant subject of discussion between my wife and I. We are both immigrants to Canada, and both of our parents migrated from their home countries in search for better opportunities (Hers migrated permanently from Spain to France, mine temporarily from Colombia to Venezuela).
Since my first migration when I was 8 years old, I have always felt extremely privileged to be welcomed in a new country. When I migrated on my own to Canada, I was extremely grateful, and later when I decided I wanted to become Canadian, I made a strong effort to assimilate to Canadian culture.
Assimilation takes many forms, but at the very least I do not think it’s unreasonable to ask immigrants of three things when they immigrate:
- Learn the official language of the place you are migrating to.
- Follow the laws and general customs of the country you are migrating to, even if they are different that where you come from.
- Do not impose your customs, culture, and religion onto others in the new country you are migrating to.
Canada is an amazing country in that it allows us the freedom to maintain our customs and practice our religions freely. I feel it is part of Canadian culture to accept and embrace the cultures of those who migrate here. However that welcoming and embracing of new cultures seems to be diminishing, and I believe this is due in part because a portion of those who have migrated here in the past decade simply have no desire to assimilate into Canadian society.
I think if we can figure out a way to encourage new immigrants to embrace assimilation into Canadian culture, Canadian society will slowly heal and go back to a place where we can all live together in harmony.
https://www.nytimes.com/2025/02/24/magazine/denmark-immigration-policy-progressives.html
Learn the official language of the place you are migrating to.
Yes, this sounds completely obvious to me.
Of course, learning languages takes time, and may be more difficult for older people. So I wouldn't expect fluent speech from the start, and maybe from the older generation even in a year or two -- just a gesture of trying. The important thing is that they do not isolate their kids and themselves from the local society behind the language barrier. Become bilingual.
Heck, if I had to emigrate somewhere, I would want my kids to speak the local language, because it expands their options. Not even as a sign of respect or thanks to the locals, but for completely selfish reasons. It will be better for my kids to have more job opportunities, more social opportunities, etc. Not doing so would be like putting my kids in a prison for a lifetime -- limiting their social interaction to the few neighbors who speak the same language.
Follow the laws and general customs of the country you are migrating to, even if they are different that where you come from.
Do not impose your customs, culture, and religion onto others in the new country you are migrating to.
Basically, be able to fit in the mainstream culture, and keep everything else on the level of "hobbies, that shouldn't annoy my neighbors".
.
There are some steps the welcoming country can do for the immigrants, such as organize cheap language courses for them. But it's on the immigrants to take that opportunity.
Rough preparation for a future where AI keeps improving and changes society as we know it:
Stay on top of developments, both on how I as an individual can use the tech to be more productive / efficient at both work and life, as well as how others are using it.
Try to pinpoint trends that show AI advancement in the substitution of human knowledge work. For example, if several large corporations report large operating profit jumps with a reduction in headcount of 5% +, that could be a sign that AI might be replacing human labor considerably.
Have a good portion of my net worth invested in equity of companies devoting considerable resources to AI. My train of thought is the following: If AI advancement stalls, then these companies will likely lose considerable value. However my day to day life would not change, meaning I will continue having a traditional job for the next 3 decades and that equity loss will be made back. If AI advancement continues, and society becomes distorted because of it, at least I will likely be considerably wealthier, which would allow my wife and I to be able to make the necessary moves to mitigate the impact / enhance our quality of life as AI permeates society. My investment portfolio is currently 40-50% directly exposed to public companies advancing AI tech.
Enjoy modern society as much as I can because things are possibly going to get real weird. Not better or worse: Just weird and different.
- If the AI race continues, I need to find a way to be a part of the winner of the AI race (Likely the United States or western society if it unites somehow) I would want to be part of the state that wins the race and pray the leaders redistribute the wealth accordingly.
If the US introduces UBI (likely mainly through taxation of AI companies), it will only be distributed to US Americans. Which would indeed mean that people which are not citizens of the country that wins the AI race, likely the US, will become a lot poorer than US citizens. Because most of the capital gets distributed to the winning AI company/companies, and consequently to the US.
I agree with the assumption that things will get weird. And I'm facing difficulties in enjoying modern society more and more often. Thanks for sharing your ideas.
Hot macroeconomic take:
Bessent / Trump are purposely lowering domestic demand via a combination of Doge + Psychology.
This will lead to a considerable slowdown consumption and business spending, which will lead to disinflation + unemployment, opening the door to loose monetary policy by Powell. I am talking about 5+ rate cuts plus a QT pause.
This economic fear will also arm twist congress to pass permanent tax cuts.
SPY finishes the year positive.
So unbelievably convenient I don't even believe it