In the unlikely event Fetterman determined he could not campaign, he would have to voluntarily remove himself from the ballot to be replaced. Then it would be up to the full Democratic state committee to determine who would replace him.

His stroke was four days before the May primary, so the timing was impossible there, but he had until August to remove himself from the general election ballot and get replaced by the party.

www.inquirer.com/politics/ele...

www.cbsnews.com/pittsburgh/n...

Instagram's app has a dedicated Reels view separate from the main feed, but it *also* populates the main feed with reels from people you don't follow if it runs out of content to show you. Those are labeled "Suggested for you".

Baumol effect - Wikipedia

The chart is just (an updated version of) the chart on the Wikipedia page for Baumol effect, *with "average hourly earnings" deliberately removed*.

en.wikipedia.org/wiki/Baumol_...

Ensemble is not very *culturally* YIMBY, though. The nerds who care about urban policy are mostly with Projet, with "bad on housing" the tradeoff being made for "good on most other things, and actually likes the city".

Montreal calls a new housing bylaw 'the most powerful in North America' but critics say it'll drive up costs | CBC News A new Montreal bylaw proposed and passed by Valérie Plante’s administration could reshape the way housing development works in the city, but not everyone is happy about it.

Ensemble is better on housing. The incumbent Projet administration brought in inclusionary zoning on steroids, and Ensemble is making it a priority to repeal that + make it easier for developers to build.

www.cbc.ca/news/canada/...

Poll showing that 54% of UCP supporters support Alberta separation, and only 39% support remaining in Canada. 2% of NDP voters support separation, and 98% support remaining.

The leaders of this initiative are Progressive Conservatives, and they seem to have a goal to wedge the governing United Conservative Party (formed by a recent merger between the PCs and further right Wildrose) in order to cause a split, purge the separatists, and revive the old PC Party.

In the way they are in other countries - private associations that band together to run candidates in support of a common project.

The specific phrasing was popularized I think by this blog post:

jwmason.org/slackwire/po...

Jane McAlevey on the Union Defeat at Amazon Labor strategist Jane McAlevey offers her take on why Amazon workers were defeated in their recent Bessemer, Alabama union drive.

They had a series of interviews with Jane McAlevey about union organizing over the years, and I always thought they were great reads.

This one from 2021, following the Amazon union defeat in Alabama, is one that sticks out in my memory: jacobin.com/2021/05/amaz...

Screenshot from Nintendo Life article reading: One such story involves the N64's Expansion Pak, a little device used to double the console's RAM from 4MB to 8MB. The tale goes that a game-breaking, memory-related bug occurred in the 4MB version and forced Nintendo to ship the game bundled with the Expansion Pak. That's a costly bug, and we certainly wouldn’t have wanted to be the one to deliver the news to notoriously fiery then-President of Nintendo, Hiroshi Yamauchi back at Nintendo HQ. That story has become more-or-less accepted fact, although Stevenson believes the truth is more complicated. "This one’s a myth. The decision to use the Expansion Pak happened a long time before the game shipped, in fact we were called in by management and told that we were going to use the Expansion Pak and that we needed to do find ways to do stuff in the game that justified its use and made it a selling point. I think the bug story somehow got amalgamated into the Expansion Pak use and became urban myth." "There was a game-breaking bug right at the end of development that we were struggling with," he clarifies, "but the Expansion Pak wasn’t introduced to deal with this and wasn’t the solution to the problem. My memory is that, like all consoles, the hardware is constantly revised over its lifetime to take advantage of ongoing improvements in technology and manufacture methods to essentially make the manufacture more cost effective and eventually profitable. I think there we’re something like 3 different revisions of the internal hardware by this point and the bug was unique to only one of these versions. We did eventually find it and fix it, but very late in the day."

The DK64/Expansion Pak thing is a myth!

www.nintendolife.com/news/2019/11...

I don't know how it's possible to watch the Chris Hayes clip from last night and conclude otherwise!

Idk what Schumer is doing, but it seems clear that Jeffries is endorsing by the weekend.

White male comedian saying: "Straight guys, we get perks. Like, we don't have dietary restrictions. A lot of women and queer folks have 'celiac', 'lactose intolerance', 'oil sensitivities'."

Comedian continuing: "Cis, straight guys, we just have years, decades, of unexplained diarrhea."

It reminded me of this joke I saw on IG last week from Alistair Ogden, playing with (and critiquing) the idea that dietary restrictions and digestive issues are somehow woman-coded? We're exploring new frontiers in gender!

Tweets from John Bresnahan, @bresreports: An angry Bernie Sanders won’t drop his support for Graham Platner despite a Nazi tattoo on his chest 2/ Sanders said Platner “as a young man” went thru some really difficult experiences” in Iraq and Afghanistan. 3/ Sanders: “I personally think he is an excellent candidate and will support him, and I look forward to him becoming the next senator from Maine.” 4/ When pressed on Platner’s Nazi tattoo, Sanders lashed out at the “corrupt campaign finance system” adding “We don’t have enough candidates in this country that will take on the powers that be and fight for the working class.”

Bernie isn't admitting he is wrong *now*.

That's right. I think it's probably easily explained by "younger people are more likely to be solely engaged at the presidential level and don't donate downballot."

The eigenslur was a great educational tool in making me think about the way "reality" is embedded in the structure of LLMs and how they store language.

The author *had* used a data series that was in real dollars. A common-enough mistake to make, but I still find it hard to dismiss this as just remixing existing text from the corpus. This was a screenshot of a chart it had never seen, with up-to-date data. There's something more going on here!

A graph charting "cumulative food price index" for OECD countries from 2015-2025, normalised to 100 for Q1 2025. For most countries, the 2025 price index ends up between 105 and 110.

Screenshot of ChatGPT conversation. User prompt: "I mean yeah that's a nice catch but I meant with the lines themselves, the results." ChatGPT answer: "Ah, got it — you mean the results in the chart, not the labeling. Looking closely at the lines: The U.S. (blue) line looks too low compared to what we know. U.S. food price inflation since 2015 has been strong, especially post-2020. By 2024, the USDA’s CPI for food at home is up ~30% from 2015, but here the index only reaches ~107. That suggests the data may have been deflated or adjusted incorrectly. Same with Canada (red) — the increase looks muted. By 2024, Canadian food prices are more like 25–30% above 2015 levels, not just ~10%. Germany (green) rises a bit more, but still looks understated compared to Eurostat data. Meanwhile, some gray OECD countries are shooting up by 20%+ (even 25%) — which is closer to reality. So the likely issue with the lines themselves is: 👉 The author deflated or double-adjusted the price indices (probably using real terms), when these should be nominal indices. A food price index already controls for the base year (2015=100); adjusting further for overall inflation or real dollars flattens the lines artificially. That’s why your friend’s U.S. and Canadian lines look oddly flat — they shouldn’t be trailing the OECD average like that."

Here's an example that isn't coding-related: someone I know posted this graph, and I wondered if chatGPT would be able to be able to tell what was off about it. At first it critiqued cosmetic stuff, but when I reprompted it, it basically nailed the question: both what's wrong, and the likely cause.

I think the MMT people partly bought themselves respectability on the left and center-left by attaching themselves to Bernie but it's a crank idea, and his senior economic advisor was a lead MMT person.

The article says that New York evaluates kids for the gifted program in kindergarten, then grade 3. It sounds like next year's class of kindergarteners aren't getting tracked for their first three years, and the article also says that Mamdani *refused to answer* if he'd end it in third grade.

They're real, yeah, there are leaked files of the album floating around.

I don't hate the song, though Taylor might be a little bit too old for the Olivia Rodrigo thing she's going for.

I don't think there's much of a reason to do that? You should graph pre-trends for the whole data set *with error bars*. Hopefully the control group's pre-trend will be roughly in the treatment group's error bars, and that + theoretical justification should be enough.

They've only *done* two "real" Universes Beyond sets so far. LotR set was the 1st one, and until Final Fantasy came out it was the most successful MtG set ever. Avatar TLA in November will be the third.

(They've been doing a lot of smaller crossover products, but the shift to full UB sets is new.)

Fig. 3 in Optimal Bandwidth Choice for the Regression Discontinuity Estimator by Imbens/Kalyanaraman. x axis is different bandwidth widths for a regression discontinuity regression, from 0 to 0.5. y axis is the coefficient for the outcome effect for each of those different bandwidths. Outcomes are plotted as a solid line chart, with dotted lines showing the confidence interval.

Either like this or as a line chart would be actively good. Showing the sensitivity of your outcome to your design choices is good practice, and is pretty similar to a "here's how our RD estimates change with different bandwidth" chart in this Imbens/Kal paper

scholar.harvard.edu/files/imbens...

Image of a homophobic slug looking unimpressed, with a banner of white text on red background reading "LIVE SLUG REACTION"

Large health insurers (or whatever Kaiser is) should have pretty good data on this, but it's definitely not the kind of thing they release publicly.

Yeah sure. "Ally".

Screenshot from church website showing bio for the dog, Bella. Top left shows music player, Bella Ciao performed by the Red Army Choir. Left shows image of Bella, a white husky. Banner has "Bella" repeating in a wave, with the tile of the page being "Ciao!"

Red Army Choir rendition of Bella Ciao, eh?

Unlikely to be him - someone named Tyler Robinson owned the house listed on the FEC form from 2019-2021, when our Tyler Robinson would have been 16-18.

Gallup had him in the 60s and 70s for most of the year, brief dip into the 50s when the economy fell off a cliff and Congress passed TARP. news.gallup.com/poll/116500/...

The Idiocy of the Epstein Mythology The Epstein mythology can be roughly defined as the popular belief, nearly ubiquitous on social media and adjacent outlets, that the deceased financier Jeffrey Epstein orchestrated a sprawling child s...

It actually looks... shockingly benign. "Epstein was a pedophile, but likely not at the head of a sprawling elite network of organized pedophilia reaching into every corner of society."

www.compactmag.com/article/the-...