Newly released footage shows an ICE agent killing Rubin Ray Martinez, 23, in his car in Texas.
"He was shot at point-blank range through his side window by an ICE agent who was in no danger."
www.bbc.com/news/article...
This is such a good point, and it just also illustrates the racist double standards where Mamdani continues to be vilified no matter how much he works on outreach, while for Plattner, there are endless supplies of grace.
And there are some pretty significant threats to the short-run situation. I think probability of recession in the next year has ticked up lately.
I think it's true that the economy is basically strolling along but could be stronger in a counterfactual where there aren't tariffs and IRA investments still exist.
And then there's the long-run situation. H1B, higher ed, ICE, science policy all long-run threats to growth.
Tillis, like Lisa Murkowski, Susan Collins, Rand Paul, & anyone else ostensibly still a "moderate" & "pro-democracy" GOP Senator, is welcome to caucus with the Democrats, giving them control of the Senate & actually fighting back against the authoritarianism, at any time.
bsky.app/profile/mcop...
If you were too young for the Iraq war, make sure you go read Judith Miller's wikipedia entry.
This is the logical endpoint of anti-anti-Trumpism: "I'm all alone. I'm afraid of everything. There's no one to trust."
All while living in a wealthy, internally peaceful society, earning a hefty paycheck, and getting regular reminders of the high status that you've enjoyed since birth.
Wait I'm sorry, are you telling me that this whole time, voters consider REPUBLICANS to be the ELITISTS!?!?!?! With the *gestures around frantically* elite discourse we have? I want to punch all the pundits in their faces.
I love that the one Trump policy from #SOTU that people don't hate is actually a Biden policy.
What to know about Trump retirement accounts www.axios.com/2026/02/27/t... #axiosmarkets
ICE is struggling to keep pace with vetting new hires during its historic recruitment push, so it's hiring officers before completing standard checks.
The agency fired five people after belatedly finding that they had outstanding warrants for their arrest.
www.reuters.com/world/ice-st...
I do think this is a good point.
I agree that the Heathcliff casting is a bit shady. But there's a not-white casting director involved here (who has, admittedly, maybe a blasé attitude towards race in fiction, but who seems pretty multicultural)
www.reddit.com/r/Fauxmoi/co...
I don't agree. Edgar is presented sympathetically and is mostly just reacting to the terrible situation he is in (if anything, the white characters wrong him) and Nelly just... happens to not be white. Her non-whiteness is not what makes her unsympathetic.
Big tariff news but interesting stuff in the GDP report too. Personal Income weakened a bunch coming into the year - growing at just 0.5% (annualized) in Q4.
Personal Income, GDP's unknown brother that measures income flows to actual households, grew just 0.6% (annualized rate) in Q4.
bsky.app/profile/aust...
Real PI grew 2% in 2025 vs 2.2% for GDP. We could see that difference open up if AI leads to higher corporate profits and lower wages. Another thing to watch!
Every category of income has weakened, and this is before the OBBO sledgehammer hits us. That's going to weaken transfers considerably. Overall, means households are facing real weakness in income in 2026.
Annual GDP for 2025 came out today, but so did its much lesser known brother, Personal Income! PI is an aggregate of income streams that actually flow to households. And it is slowing considerably: 0.9% real growth in the second half vs 2.6% in the first half.
Very cool, I'll take a look! Your links didn't work for me but I assume you meant these:
www.karlwhelan.com/Papers/Kalsh...
cepr.org/voxeu/column...
Yeah, we gotta build trust somehow, and it's hard to do when the government is being run by corrupt liars.
Seems like we could use a new review now that we have lots of prediction markets that are wide open to the public allowing bets across many different domains.
A tortie cat on top of some cabinets looking down
Do we have a large scale evaluation of how good betting markets across different domains? I'm sure they're good for sports, I'm less convinced of their general wisdom.
Never nudes, clearly.
I'm leery of the arguments that "less educated" immigrants (e.g., CBO below) tend to lower US total factor productivity.
1st, the categories seem blunt if not classist. 2nd, why doesn't a non-STEM immigrant's willingness to work at lower wage than others increase TFP? Are employers being fooled?
Article: The political effects of X’s feed algorithm Abstract: Feed algorithms are widely suspected to influence political attitudes. However, previous evidence from switching off the algorithm on Meta platforms found no political effects1. Here we present results from a 2023 field experiment on Elon Musk’s platform X shedding light on this puzzle. We assigned active US-based users randomly to either an algorithmic or a chronological feed for 7 weeks, measuring political attitudes and online behaviour. Switching from a chronological to an algorithmic feed increased engagement and shifted political opinion towards more conservative positions, particularly regarding policy priorities, perceptions of criminal investigations into Donald Trump and views on the war in Ukraine. In contrast, switching from the algorithmic to the chronological feed had no comparable effects. Neither switching the algorithm on nor switching it off significantly affected affective polarization or self-reported partisanship. To investigate the mechanism, we analysed users’ feed content and behaviour. We found that the algorithm promotes conservative content and demotes posts by traditional media. Exposure to algorithmic content leads users to follow conservative political activist accounts, which they continue to follow even after switching off the algorithm, helping explain the asymmetry in effects. These results suggest that initial exposure to X’s algorithm has persistent effects on users’ current political attitudes and account-following behaviour, even in the absence of a detectable effect on partisanship.
Figure 2. ITT estimates of feed-setting changes on engagement and political attitudes. ITT effect estimates of switching the algorithm on and off (in s.d.). Left, effect of moving from the chronological to the algorithmic feed for users initially on the chronological feed. Right, effect of moving in the opposite direction for users initially on the algorithmic feed. For each outcome, the results of two specifications are reported. Blue, unconditional estimates with robust s.e., controlling only for the initial feed setting and, where applicable, pre-treatment outcome levels. Orange: conditional estimates, controlling for pre-treatment covariates using GRFs; 90% and 95% CIs are reported. Numerical effect sizes and P values correspond to the conditional estimates (all tests are two-sided). The unit of observation is respondent. From top to bottom, sample sizes are n = 4,965, n = 3,337, n = 4,965, n = 4,965, n = 4,596, n = 4,596 and n = 4,850. Tests are described in Methods. Supplementary Information Table 2.16 reports the exact numerical point estimates, s.e., CIs and sample sizes for every specification. All outcomes are standardized. Additional results are presented in Supplementary Information section 2. PCA, first principal component from principal component analysis.
X's algorithm is in fact doing what you think it's doing. www.nature.com/articles/s41...
Once again frustrated by how Gemini uses my previous answers. I could probably fix this with clever prompting (I don't find that starting a new session helps actually). In this case, it knows I research inequality, so it shades answers in that direction, which doesn't feel like fair analysis.
Q: Take a look at this graph: https://fred.stlouisfed.org/graph/?g=1S4pj It's the difference between GDP and Personal Income in the U.S. over the past 27 years or so. I want to ask you a couple questions about it. The first is about the big spikes in Q4 of 2012 and Q1 of 2013. What do you think caused those? Gemini said The spikes in Q4 2012 and Q1 2013 on that FRED graph are primarily a result of the "Fiscal Cliff" and the behavioral responses of taxpayers and corporations to anticipated tax law changes. Because the graph shows the difference between GDP and Personal Income, these spikes represent moments where Personal Income moved sharply relative to the broader economy. Here is a breakdown of what happened: 1. The Q4 2012 Spike: Income Acceleration In late 2012, the U.S. was facing the "Fiscal Cliff"—a series of scheduled tax increases (including the expiration of the Bush-era tax cuts and the payroll tax holiday) and spending cuts set to take effect on January 1, 2013.
Playing around with AI a lot lately for econ analysis. Asking it to explain things I know the answer to, to see how well it does. This is a pretty simple one, but both Gemini and Claude did really well.
Seems increasingly clear that even if it's not economically optimal to boost taxes on high incomes, you have to do it anyways cause these guys are fucking crazy.
Pardoning drug lords but deporting sick little kids straight from the hospital really sums the whole thing up doesn’t it
