Tyler Brendall

[Tyler Brendall @tydog99]

What a bullshit stunt and a duplicitous tweet by @VP. Hey @VP and @realDonaldTrump how about doing your actual jobs and not stir up shit. https://t.co/VeW4pJSFcE

[IndyStarSports @IndyStarSports]

The VP tweeted a photo of himself at a #Colts game today. About that photo … https://t.co/pJKPy34D9M

[PMT Stats @PmtStats]

Imagine drafting both of them in the same draft

Deciding you want neither of them

Only getting one 1st rounder, 29 games of Anthony Davis, and Max Christie in return

[Tyler Brendall @tydog99]

@lukebayes But when JavaScript? 🤣

[Shane Cashman @ShaneCashman]

Iran’s imaginary nuke is why we can’t afford gas. Data centers are driving up energy bills and devouring farmland. Our leaders are throwing fake UFOs at us to distract us from Epstein. At least the ballroom is twice the size now.

[Donald Trump Jr. @DonaldJTrumpJr]

Remember when they said Trump would get us into a full-blown war with Iran?

Times like these should make us all realize how lucky we were to have Trump, his strength and his resolve.

[Gavin Newsom @GavinNewsom]

No vote in Tennessee (+1 GOP)
No vote in Florida (+4 GOP)
No vote in Missouri (+1 GOP)
No vote in North Carolina (+2 GOP)
No vote in Texas (+5 GOP)

Virginia’s voter-approved maps thrown out.

MAGA has rigged the system.

[Mayne @Tradermayne]

Just finished book 4 of the the Red Rising series.

Aggressively pushing them on my friends and family.

Get me a ref link Pierce.

Please give me some suggestions for similarly good books.

I'll be done the 2nd trilogy in a couple weeks MAX.

[Tyler Brendall @tydog99]

Corruption at the highest levels. Good old America.

https://t.co/52vXOxhTzH

[Tyler Brendall @tydog99]

@lukebayes It's magic dude!

[Lyn Alden @LynAldenContact]

@MarioNawfal He can't name his favorite Bible verse. He forgot to put his hand on the Bible during his swearing in.

When Pope Francis died, he posted a pic of himself as Pope. Then he criticized the next Pope and posted a pic of himself as Jesus.

It's not strange or unclear.

[Congresswoman Sarah McBride @Rep_McBride]

In a political career defined by grotesque statements, this president’s horrifying, illegal, and genocidal threat this morning is among the most dangerous and appalling.

You can’t shout “fire” in a crowded theater and a president cannot be allowed to threaten genocide with the United States military. Threats of war crimes and disregard for human life must be met with accountability under the law.

Trump must go—and Republicans, whether in the Cabinet or Congress, must join Democrats in using any and all constitutional powers at our collective disposal to end this illegal war and take the gun out of this madman’s hands.

[Former Congresswoman Marjorie Taylor Greene🇺🇸 @FmrRepMTG]

25TH AMENDMENT!!!
Not a single bomb has dropped on America. We cannot kill an entire civilization.
This is evil and madness.

[Former Congresswoman Marjorie Taylor Greene🇺🇸 @FmrRepMTG]

On Easter morning, this is what President Trump posted.
Everyone in his administration that claims to be a Christian needs to fall on their knees and beg forgiveness from God and stop worshipping the President and intervene in Trump’s madness.
I know all of you and him and he has gone insane, and all of you are complicit.
I’m not defending Iran but let’s be honest about all of this.
The Strait is closed because the US and Israel started the unprovoked war against Iran based on the same nuclear lies they’ve been telling for decades, that any moment Iran would develop a nuclear weapon.
You know who has nuclear weapons?
Israel.
They are more than capable of defending themselves without the US having to fight their wars, kill innocent people and children, and pay for it.
Trump threatening to bomb power plants and bridges hurts the Iranian people, the very people Trump claimed he was freeing.
On Easter, of all days, we as Christians should be reminded that the son of God died and rose from the grave so that we can be forgiven once and for all of our sins. Jesus commanded us to love one another and forgive one another. Even our enemies.
Our President is not a Christian and his words and actions should not be supported by Christians.
Christians in the administration should be pursuing peace. Urging the President to make peace.
Not escalating war that is hurting people.
This NOT what we promised the American people when they overwhelmingly voted in 2024, I know, I was there more than most.
This is not making America great again, this is evil.

[Earth @earthcurated]

NOT FLAT…

[eisha 🍒 @meishato]

Americans be like: death penalty is great and war is good and I deserve to have 10 guns but abortion is murder

[Richard Hanania @RichardHanania]

A hilarious example of how much the administration lies and just how lacking in virtue these people are.

DHS posted a meme with the phrase "We'll have our home again," a phrase from a white supremacist song.

When asked about it by the NYT, Tricia McLaughlin denied that the phrase was related to the song: "There are plenty of references to those words in books and poems."

A NYT reporter points out that when you open the post on Instagram, the white supremacist song itself starts playing.

McLaughlin denies this is true and accuses the reporter of spreading a left-wing conspiracy theory! She says he is the one "mainstreaming racism."

They then delete the post 40 minutes after the interview.

These people just have no honor. They're hateful racists, but not even courageous enough to be honest about it. They lie like most people breathe, and when caught, pivot to another lie. To live like this degrades the soul.

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Andrej Karpathy @karpathy]

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.

[The Green Dragon Tavern @greendragonhq]

@JDVance To clarify,

9 out of 10 states that have the highest murder rates are Republican lead.

9 out of 10 states with the lowest murder rates are Democrat lead.

Republican states are the violent ones

[gainzy @gainzy222]

I never want a single person to make fun of the sausages I eat again

Bro is literally cooking engineered turds

[Aaron Reichlin-Melnick @ReichlinMelnick]

THREAD: Judge Ellis is the first federal judge to review extensive body cam video of DHS's actions in Chicago. She finds that DHS *repeatedly* misled the public and made claims that were disproven by agents' own videos.

I'll go through some of the most egregious ones here.