ai girlfriends might wreak havoc on society. they might also be a huge boon in the loneliness epidemic. @jackiesnow.bsky.social spoke to men about the tricky balance between being enamored with a chatbot and leaning on it for extra support www.gq.com/story/ai-gir...
Can someone explain how giving Grok AI GF mode gets us to AGI
And last time I checked, they have no models, minimal research, and use humans to improve models with a method that Hinton just called "a pile of crap."
This chef had her cooking responsibilities taken away and given to robots that customers complained couldn't make the food as good as hers. Now she does the dishes, despite us having robots, called dishwashers, that are actually very good at that. restofworld.org/2025/robot-c...
Read the full story about these four exceptional journalists on our website: ista.ac.at/en/news/the-...
"Letter after letter showed me a refreshing disregard for that invisible tyranny of taste determining what we 'should'—even 'must'—read."
@jackiesnow.bsky.social for @lareviewofbooks.bsky.social:
Learning prison regulations felt like studying for a degree in carceral bureaucracy. Behind every rejection lurked an institutional paranoia: hidden messages, drugs or seeds of discontent that might blossom into unrest concealed within innocent pages. Must-read!
lareviewofbooks.org/article/read...
Please do!!! I've been meaning to email folks with a link :)
If you read this and are so moved, purchases for @dcbookstoprisons.bsky.social are doubled now through May 5. bookshop.org/wishlists/a6...
"What our incarcerated readers demonstrate is that true literary autonomy is about the right to seek what speaks to our individual humanity rather than institutional expectations." @jackiesnow.bsky.social on what she learned about reading from DC Books to Prisons. lareviewofbooks.org/article/read...
Fair, I'd make this by beach and puttering around jalopy so I could get by (especially if we get/steal/improve upon BYD's 5-minute full charge tech)
Can't tell if the rear cab wall goes down and if my board would fit, but this could be my new dream truck
how fancy superyachts found their purpose ~ by @jackiesnow.bsky.social
🐋🛥️ www.fastcompany.com/91319437/lux...
I bought two copies of @georgetakei.bsky.social's Nos Llamaron Enemigo (They Called Us Enemy Spanish Edition). We get a ton of Spanish requests and never have enough books to send. There are lots of other fun titles you can get to help incarcerated readers out!!
Starting today in celebration of Independent Bookstore books donated off our wishlists found here - linktr.ee/dcbtp will be matched by a generous donor. Help us send books to prisoners and support independent bookstores! #BooksToPeopleInPrison #IndieBookstoreDay
![chatgpt log:
What would be an easy way to calculate the tariffs that should be imposed on other countries so that the US is on even-playing fields when it comes to trade deficit? Set minimum at 10%.
Reasoned about trade tariffs and deficits for 10 seconds v
A straightforward (if naïve) method is to set the tariff rate for each trading partner equal to the percentage share of the trade deficit relative to that country's total imports-always no less than 10%. In formula form:
Tariff Rate (%) = max(10, (Trade Deficit ÷ Total Imports) *
100)
For example, if the US runs a $20 billion deficit on $100 billion worth of imports from a country, the calculated rate is (20/100)×100 = 20%. If the deficit were only 5%, you'd still impose a 10% floor.
This method ignores the intricate dynamics of international trade-such as elasticities, retaliatory measures, and supply chain nuances-but it provides a blunt, proportional rule to "level the playing field." One might implement it in Python like so:
[code]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:iyz5zf463ic52vqbonyu2ebu/bafkreigbalqxjorllnpelbwe5kcla5fdedxvgv3cicxdsrbdxarodif5ba)
chatgpt log: What would be an easy way to calculate the tariffs that should be imposed on other countries so that the US is on even-playing fields when it comes to trade deficit? Set minimum at 10%. Reasoned about trade tariffs and deficits for 10 seconds v A straightforward (if naïve) method is to set the tariff rate for each trading partner equal to the percentage share of the trade deficit relative to that country's total imports-always no less than 10%. In formula form: Tariff Rate (%) = max(10, (Trade Deficit ÷ Total Imports) * 100) For example, if the US runs a $20 billion deficit on $100 billion worth of imports from a country, the calculated rate is (20/100)×100 = 20%. If the deficit were only 5%, you'd still impose a 10% floor. This method ignores the intricate dynamics of international trade-such as elasticities, retaliatory measures, and supply chain nuances-but it provides a blunt, proportional rule to "level the playing field." One might implement it in Python like so: [code]
Gemini answer: Okay, let's break down the idea of using tariffs to achieve an "even playing field" defined as eliminating the US trade deficit. While the goal of balancing trade is understandable, devising an "easy way" to calculate tariffs to achieve this is extremely complex, and most economists would argue it's not feasible or desirable for several reasons. However, let's outline a highly simplified conceptual approach based only on the numbers, ignoring the vast real-world complexities and consequences: Simplified (and Problematic) Calculation Idea: 1. Identify the Bilateral Deficit: Determine the trade deficit the US has with a specific country (Country X). Deficit_X = Value of Imports from X - Value of • Exports to X 2. Target Reduction: The goal is to reduce imports from Country X (or increase their cost to US buyers) by the amount of the deficit, so that the value effectively balances out. 3. Calculate Required Tariff (Ignoring Economics): • If you assume, very unrealistically, that a tariff directly reduces the value of imports by a corresponding percentage (which it doesn't - it increases the price), you could try: Required Reduction % = Deficit_X / Value of • Imports from X
Claude: What would be an easy way to calculate the tariffs that should be imposed on other countries so that the US is on even-playing fields when it comes to trade deficit? Set minimum at 10%. To calculate tariffs that could theoretically level the playing field for trade deficits, I'd suggest a straightforward approach based on the trade imbalance percentage: 1. Calculate the bilateral trade deficit with each trading partner: Trade Deficit - US Imports from Country - US Exports to Country 2. Express this as a percentage of total bilateral trade: Deficit Percentage - (Trade Deficit / Total Bilateral Trade) × 100 3. Apply a tariff rate that corresponds to this percentage, with your minimum 10% floor: Tariff Rate = max(Deficit Percentage, 10%) This creates a proportional response where countries with larger trade surpluses with the US would face higher tariffs. For example: • If Country A has a 25% trade surplus with the US (meaning the US has a 25% deficit), apply a 25% tariff • If Country B has a 5% trade surplus with the US, apply the minimum 10% tariff This method is relatively simple to calculate and directly ties tariff levels to trade imbalances. However, I should note that economists generally caution that trade deficits alone don't necessarily indicate unfair trade practices, and tariffs can have complex economic consequences including increased consumer prices and potential retaliation. Would you like me to elaborate on any part of this approach or discuss potential refinements to make it more sophisticated?
![Grok:
the deficit. The deficit as a percentage of total trade is
$295B/$582B = 50.69%. Using the formula Tariff% = 10% +
(Deficit% × Scaling Factor), we choose a scaling factor of 50 for illustration:
• Tariff = 10% + (50.69% × 50) = 10% + 25.345% = 35.345%, rounded to 35.3%.
This means a 35.3% tariff on Chinese goods could be proposed to offset the imbalance, aiming to reduce imports and encourage domestic production or exports.
Extending to Other Countries
To provide a broader view, here's a table of top US trading partners with 2024 deficits, using data from The Motley Fool and similar calculations (assuming scaling factor of 50 for consistency):
[data table headings]
Country
Deficit
(USD
Billion)
Total
Trade
(USD
Billion)
Deficit %
Calculate d Tariff %
China
-295
582
50.69%
35.3%
Mexico
-172
840
20.48%
20.2%
Vietnam
-123
(Data incomplet e, estimate)
~30%
25.0%
Ireland
-87
(Data incomplet e, estimate)
~25%
22.5%
Germany
-85
(Data incomplete estimate)
~20%
20.0%](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:iyz5zf463ic52vqbonyu2ebu/bafkreietqlxsi5akdrvtp2rwqpc6kt6g6bbb2dppqcfn2j4q7xkofn4f4y)
Grok: the deficit. The deficit as a percentage of total trade is $295B/$582B = 50.69%. Using the formula Tariff% = 10% + (Deficit% × Scaling Factor), we choose a scaling factor of 50 for illustration: • Tariff = 10% + (50.69% × 50) = 10% + 25.345% = 35.345%, rounded to 35.3%. This means a 35.3% tariff on Chinese goods could be proposed to offset the imbalance, aiming to reduce imports and encourage domestic production or exports. Extending to Other Countries To provide a broader view, here's a table of top US trading partners with 2024 deficits, using data from The Motley Fool and similar calculations (assuming scaling factor of 50 for consistency): [data table headings] Country Deficit (USD Billion) Total Trade (USD Billion) Deficit % Calculate d Tariff % China -295 582 50.69% 35.3% Mexico -172 840 20.48% 20.2% Vietnam -123 (Data incomplet e, estimate) ~30% 25.0% Ireland -87 (Data incomplet e, estimate) ~25% 22.5% Germany -85 (Data incomplete estimate) ~20% 20.0%
guess where they got their weird trade deficit math from?
i went to the pit for y'all and brought back the screenshots with alt text
I am now looking at pages from his most recent book and sure, maybe (probably) he used a ghostwriter, but this doesn't seem to be the writer who sent that text. Em-dashes didn't get spaces on either side, and these are some wannabe Hemingway sentences.
Anyway, would love to know if anyone has done any sort of AI safety work around this warfare use case
Her hunch was from all the em-dashes, which is a fair tell. The thing that is screaming ChatGPT to me is the numbered list. There was an update, maybe a few months ago, that made both ChatGPT and Claude LOVE to throw in a numbered list in the middle of outputs.
This woman on TikTok argues that Pete Hegseth used ChatGPT in that bomb planning Signal group, and I think she's right. I would do almost anything to see Hegseth's prompt engineering to get the messages he sent.
For @fastcompany.com: I wrote about how @safetychanges.bsky.social is tracking how AI companies' safety promises are changing as the Trump administration rolls back the few AI rules we have (spoiler: it's not usually to make us safer) www.fastcompany.com/91304014/thi...
AI, it's just like us: when operating a vending machine business, AI will contact the FBI when it feels it's being illegally charged a business fee (I use all these verbs nouns very loosely), via @jackclarksf.bsky.social's newsletter: substack.com/home/post/p-...
Increasingly frustrated with The Times coverage of AI and how little follow up there is to claims like "AGI is nigh" and "Agents will be a useful tool in 2025."
The Los Angeles Times has removed its new AI-powered “insights” feature from a column after the tool tried to defend the Ku Klux Klan
As the kids used to say, this is extremely my shit
2021: We’re gonna invest half a trillion and create 20,000 U.S. jobs!
2025: We’re gonna do it for real this time!
Yes, agreed, but also can we talk about the art on your latest piece? The running form for the Microsoft robot has me wondering if there is a hidden message there??
