Socials: - x.com/rapatel0 - linkedin.com/in/rapatel0 ---
- rapatel0I have a feeling this will be solved somehow with peptides in the long run
- McDonalds has a franchise model and is in 100 markets. There are several thousand individually owned companies with various groupings of regional owners each of which needs to have delivery, logistics, costing negotiated and setup. There are also the compliance and trade aspects of being in basically every country.
Coke is a probably 90% margin product for macdonalds. Not sure i believe the 1B number. It's probably higher if you consider all the various coke products including and the juice that they sell.
Pepsi actually owns taco bell, burger king, etc which are direct competition. So the partnership with McDonalds is strategic.
It's easily worth having a top level exec.
- Circumstances behind the event:
- A group of local muslims were found to set fire to a train of Hindu pilgrims/kar sevaks returning from Ayodhya (Holy city in Hinduism)
- There was a large scale riot (1000-2000 people) that broke out
- Modi was accused of slow deployment of forces and tacit approval.
- Modi was cleared of all charges after a multi year investigation.
Ethnic tension between Hindus and Muslims goes back a millennia at least.
- Yeah. all you have to do is look at "Apple (lack of) Intelligence" to know that Steve's presence and taste is gone.
User: "Siri, <insert question>"
Siri: "I cannot answer that right now" <end conversation>
User: <follow up question, but then user realizes that siri has ended the conversation, so they prefix again with Hey Siri> please ask chatgpt < insert question>
Siri: "Hello, sure I can ask ChatGPT · Check important info for mistakes"
ChatGPT: "Hello, how can i help you today"
User: <insert question>
ChatGPT: Answers question and siri terminates conversation
User: <asks follow up question, but then user realizes that siri has ended the conversation, user then goes to settings and disables apple intelligence>
Egregious...
- Totally in agreement that we always read a lot from the conclusions based on data. Data often obfuscates.
I do think, however, that empiricism is a better framework for grounding outcomes in reality than pure ideology. Pure ideology (either way) is usually just confirms biases by cherry picking data.
- So I tried a few disparate books independently:
- Guns Germs and steel - The Alchemist - The Ramayana (a few others)
Harry Potter and the sorcerers stone came up in all of them near the top. :D
- OP was specifically talking about the 20s, 30s, 40s but just to add a complete picture.
Just to add some empiricism to the conversation
Fiscal Year Tariffs/Customs Individual Income Corporate Income Top Marginal Rate Receipts (% GDP)
-----------------------------------------------------------------------------------------------------------
1928 14.0% (approx) DNF DNF 25.0% DNF
1935 8.4% 14.6% 14.7% 63.0% 5.1%
1940 6.1% 13.6% 18.3% 81.1% 6.7%
1944 0.9% 45.0% 33.9% 94.0% 20.5%
1952 1.2% (approx) 42.2% 32.1% 92.0% 19.0%
1960 1.3% (approx) 42.0% 23.0% 91.0% 17.8%
1970 1.1% (approx) 46.0% 18.0% 71.8% 17.9%
1980 0.8% (approx) 47.0% 12.0% 70.0% 18.9%
1990 1.3% (approx) 45.0% 9.0% 28.0% 17.8%
2000 1.1% (approx) 49.0% 11.0% 39.6% 20.0%
2010 1.2% (approx) 41.0% 9.0% 35.0% 14.6%
2015 1.3% (approx) 47.0% 10.0% 39.6% 17.6%
2019 2.0% (approx) 50.0% 7.0% 37.0% 16.3%
-----------------------------------------------------------------------------------------------------------
DNF=Did not find
- Tariffs fell from ≈14% of receipts in 1928 to <1% by WWII -> income taxes replaced trade duties.
- Individual income taxes overtook all other sources after 1943
- Corporate shares peaked during war mobilization (~⅓ of revenue in 1944–52).
- Top marginal tax rate was surprisingly not too corrilated to government revenue.
(REALLY wish HN did basic markdown formatting)
- In the 20s-40s (pre-ww2), tax revenue was ~2% of GDP. It is currently >20% of GDP
It's a spending problem. You're anchoring on a talking point with out actually running numbers.
Don't believe me, run the numbers yourself.
- The economic theory of MAGA, is that the united states yes rebuilt the world but also exported the US consumer economy through asymmetric nonreciprocal tariffs. Rebuilding countries made money by selling to the US consumer, not the other way around.
You can argue that it's overall bad for the economy, but I think you're missing the arguement.
- You're describe an age where the government was a wash with surplus dollars. Secondly, most of these research institutions run as non-profits that effectively just cover costs (but run a large hedge fund as a side business)
The escalation in costs have come from: - Incentives around US News College rankings (and the amenities that drive the rankings) - Administrative (non-teaching, non-research) bloat
Research is definitely in need of reform though, but not sure these outcomes are actually causal or even corrilated.
- There has never been a better time to build. The vast majority of executives likely don't comprehend AI and it's capability. (I'm not talking about silicon valley) I'm talking about everything else.
The highly likely scenario is that: - These people will spend money on "AI" to solve stuff to keep their job - These people will be so slow to respond that they are ripe for disruption/exit.
- Duckdb can run as a local instance that points to parquet files in a n s3 bucket. So your "auth" can live on the layer that gives permissions to access that bucket.
- I think that this is actually the biggest threat to the current "AI bubble." Model efficiency and diffusion of models to open source. It's probably to start hedging bets on Nvidia
- If robots are a better partner, then maybe your are not that great a partner...
- Edit: my last calculation is wrong. I inverted it 350 Million will be allocated for indirects (650 Million for research)
- It's not misinformation. You are repeating a misleading talking point. Here's what happens.
- Professor & students get a grant application for 100K.
- University charges indirects at a ratio (0.55)
- 155K gets transferred from treasury to the university account.
That extra 55K comes from the money that congress allocated for grants, so if congress allocates 1 billion dollars -> 450 million will actually go to professors for research. (less than half).
I don't know about you but the universities I went to were rarely ever building new labs or buildings. Furthermore, those large projects always have state grant money coming out of another funding pool.
Glossing over some details, but the fact of the matter is that it's opaque.
- > I read or heard someplace that at many universities tuition paid by students in the social sciences is effectively subsidizing the STEM fields
I'm very skeptical of this claim.
In fact up until a recent funding method change from the Trump Administration, most grant money was subject to "overhead"--a nebulous nonsensical accounting trick that allowed the university administration to get upwards of 60% of the dollars that are earmarked for grants. If you invent something, the school will take 70% of the revenue from the innovation. Much like VC, some big wins can power the school for years.
Actually, most highly productive research universities use the research as a prestige magnet and marketing tool to help grow endowments and keep up in the US News college rankings.
I would be great if the funding weren't so opaque. We may be able to find accounting info for the public univeristies. I would bet money that, Liberal arts tuition likely goes into administration, endowments, and campus improvements for student life (better food in the dining halls...)
- Indeed this problem could become worse. Dark patterns are darker when you cannot see them at all
- I suggest you xpost to Bryan Johnson's Blueprint community. I think might help you get a lot more food tested. That community is probably ICP and also can amplify the message.