seth

if you lit a movie like this today theyd kill you

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.

this is literally the only thing I know about Niels Bohr

@ooooftw BBM is such a crapshoot tourney

i just added ROI data to the Historical BBM dashboard. so now you can see who won money in BBM4/5 and all their other metrics pretty interesting how out the top 10 drafters with the highest round 2 advance rates in BBM5, only 3 of them had a positive ROI👀

@ooooftw I can get you the data if you tell me how

unfortunately i only have access to the data for contests i entered. all due respect to bbmdb guy but if @Underdog ever wants to hook me up with the data i can make way more contest dashboards

@ooooftw This is awesome. I couldn’t find my name and then I realized I’m only in the finals for First Quarter 2. Are you able to add that as well?

made it to the First Quarter finals this week? or maybe you just want to see what the finals data looks like? come enjoy the sweat. i just published a new dashboard where you can see Player Ownership %s as well as the 374 teams that are competing

@ChessLiam I agree that the full set of 150 will have more diversity for the 25/150 than the 100/150, but why would we expect the 25 that advance to be more diverse than the 100 that advance? We don’t really have indication that there’s diversity within the 25, do we?

People who advance 25/150 BBM teams are more likely to have a team in the best ball mania finals than those who advance 100/150. The reason is the 25/150 will have more diverse teams in general. The 100/150 drafter could put 10 teams in the finals if their narrow pool runs

@Diablo_II Did you scrape this data or how did you get it? And do you have plans to add Weekly Winners?

I've updated the Eliminator page to include player searches and scoring. You can search for your own teams, teams with/out specific players, or both. You'll see current advance rates, plus the ability to see the lineup scores

going through the car wash with a basket of dirty laundry strapped to the roof

yes

@ChessLiam Inertia, plus continued fears that his snap rates can trend the wrong way

If Travis Hunter would have gone ahead of Tet McMillan just as a pure wide receiver, all signs are pointing to him playing the majority of offensive snaps, and he almost certainly plays for a better offense. Why does Travis Hunter go after Tet McMillan by a full round in drafts?

@smitchell17 I prefer it with the emojis for what it’s worth

@FF01310 Thanks man! I’ll keep that in mind!

Biggest Camp News 8/5: - Tory Horton lands in the huddle w/the 1's for third-straight camp practice! Teammates calling him "Jerry Rice Jr".🚀🚀 - Unofficial Jag's depth chart shows Travis Hunter starting WR, back-up CB. 🤓 - Injuries to Kenny Pickett & Dillon Gabriel push CLE to sign 5th QB in Tyrone "Snoop" Huntley. Rookie Shedeur Sanders listed as 4th-string QB on "unofficial" depth chart. - Kayshon Boutte continues standout camp, pushing as favorite to start at "X" in Josh McDaniel's offense. - Chase Brown set to expand role in the passing game compared to last season? 📈 - With Issac Guerendo sidelined for a few weeks, Jordan James returns to SF camp, looks fast in return. CMC cuff? 🤲 - OC Kliff Kingsbury on 2nd-yr WR Luke McCaffrey, "He's come a long way from last year, just the confidence, we’re playing him outside a lot for necessity, he’s definitely night & day difference from what he was last year @ this time” - Elijah Arroyo showing up BIG in camp, goes for 100+ RecYds in Monday's camp practice! 👀 - Mason Taylor second-straight DNP due to high-ankle injury, could miss a few Weeks. 🤕 - Texans "unofficial" depth chart has slot demon Christian Kirk 😈, Higgins at "X", alongside Nico Collins (rookie Jaylin Noel back-up slot). - A.J. Brown sitting for 3rd consecutive practice as he continues to deal w/hamstring injury. 😬 - NYJ starting QB Justin Fields struggling a tad in camp, just 8-of-32 in last three camp practices overall w/an INT. 📉 - Schefter reports on Rams QB Stafford: "Sounds more like a maintenance issue where they’re being smart w/37-year-old QB. They (LA) feel like if there were a game today, Stafford would be able to play." - Alexander Mattison cited for short-yardage area of focus were MIA struggled last year, but also having a very impressive camp breaking long runs & hitting the hole w/head of steam. - Reports from Saint's beat: "Spencer Rattler easy decision as starter right now", as Rattler gets the start w/1's for 2nd-straight day in camp (hasn't been done yet for any QB). 🤔 - Rams ink their star RB Kyren Williams for 3 more years, worth up to $33M, $23M in guaranteed $$. 🚀 - Tucker Kraft returns to practice! 🥳 - Rookie RB Bhayshul Tuten logs best practice of camp so far, one especially impressive downhill run that saw him bounce off contact for nice, positive yardage. - Nick Chubb flashes some potential upside? Best day of camp for the vet RB getting snaps for injured Joe Mixon. - A.D. Mitchell COOKIN' in camp? We still believe! 🧑‍🍳 - Dolphin's newly acquired TE, former rapper Darren Waller, said to be "On track for Week 1", per his Agent.

this is the guy in your pfp btw

@tjlaessig @MileHighFF58 @goblore_dfs Make it obvious from the confirmation popup whether we’re entering a fast or slow draft and that’d help a lot

@MileHighFF58 @goblore_dfs That is not done purposely, it is just the process is very manual. So if the pre-set amount of fast drafts runs out, it will be slows only available until we manually add more fasts back. We are working to better automate this process, agreed it creates a frustrating experience.

All Underdog drafters should ban together to boycott pick ems until they fix their drafting side. That’s probably the only thing they would care about at this point.

@JewishMcCaffrey Travis Hunter going 180 when tourneys first launched

Feels like Best Ball this summer has had the most insignificant ADP fluctuations of any year. Am I wrong? Are there any big CLV victory laps? CMC in the 1.09-1.12 range for one month. Jefferson falling to 1.06 recently due to injury. Pickens a few rounds of CLV pre trade. Some backup ish RBs moving from like 16th round to 12th round. Was that basically it? Still time left but would need to be a significant injury to a star player at this point.

@SBlum2711 @UnderdogDrafts could help us out by displaying clearly on the confirmation pop-up if it’s Slow or Fast drafts we’re entering

Just accidentally regged seven 20 second BBMs at once. Wouldn’t wish that experience on my worst enemy.

@Cheeseboogler @Underdog I did this on accident one time and I’m still mad about it

Just did a @Underdog BBM… The Chase team at the 1 spot passed on the burrow fall for the stack at the 6/7 turn. With no QB. Sheesh.

there’s a nonzero chance that Jordan Addison outscores Justin Jefferson

My four candidates for great AI art

Obama weighs in on Abundance: