Brice Morrison (@BriceMo) profile picture

Product @ Meta

Bay Area, CA
Joined March 2009
Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)Photo by Brice Morrison (@BriceMo)
Brice Morrison retweeted
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.
1,630
5,568
1,458
40,714
7,869,669
Brice Morrison retweeted
I’m gonna give 10 random people that repost this and follow me $25,000 for fun (the $250,000 my X video made) I’ll pick the winners in 72 hours
367,968
2,459,130
219,967
1,806,115
286,928,209
Brice Morrison retweeted
there are a lot of things you want to do that you are never going to get done. embracing that is the key to accomplishing the things you *really* want to do.
251
892
115
6,891
761,689
9
25
1
225
Brice Morrison retweeted
To get things we haven’t gotten, we need to do things we haven’t done.
11
22
2
136
Brice Morrison retweeted
I do not have “magical” discipline and focusing ability — I struggle with distractions like everyone else. Often it is better to just remove the option to distract yourself instead of fighting he urges. When I decided to get serious about my AI work, I made a few changes: \
69
412
93
4,743
The misconception that there is no sound in space originates because most space is a ~vacuum, providing no way for sound waves to travel. A galaxy cluster has so much gas that we've picked up actual sound. Here it's amplified, and mixed with other data, to hear a black hole!
11,371
102,129
33,642
411,410
I have a design tool I call "Don't Solve the Hard Problem"
11
198
41
1,064
Brice Morrison retweeted
ADOP: Approximate Differentiable One-Pixel Point Rendering abs: arxiv.org/abs/2110.06635
62
963
361
4,872
Replying to @evernote
@evernote @evernotehelps Why is there no button to force sync on Mac? Can we please add it? My workflow goes back and forth between mac and mobile. Often I need to get the most recent version of the note and don't have time to wait 10m for auto sync.
1
Current workaround: restarting Evernote to force a sync. Seems ridiculous. I've been a paid member for over a decade. 2020 expectation is that everything instantly auto-syncs like Google Docs. If we can't deliver that, at least allow force sync. This seems like a step backward
Brice Morrison retweeted
Thank you for making the drive into base camp sweet. 🔥 🚒 #Allthefeels
6
16
2
131
Brice Morrison retweeted
"And you can also commit injustice by doing nothing." - Marcus Aurelius
14
754
37
2,168
Brice Morrison retweeted
The difference between sounding smart and being smart is “I don’t know.”
203
2,771
162
13,754
.@coffeetalk_game is finally out! It costs me time, money, sleepless nights, countless tears, and several heartbreaks to bring this game to you. It will only cost you $12.99 to get it. So please do give it a try or help spread out the words!
41
408
52
861
Brice Morrison retweeted
website: THINGS TO DO TO AVOID DEATH me: ok i should read this one! website: you have reached your article limit best of luck
7
88
3
1,324
BEST DUO IN THE WORLD! 🏆 Congrats to @CoolerEsport’s @aquaa & @nyhrox, your first #FortniteWorldCup Duos World Champions & winners of the $3 Million top prize!
1
10
4
103
3 v 3 "Arena scale" Oculus Quest demo at #OC5 Playing Dead and Buried.
6
33
4
77
Loved @NateSilver538 ‘s @FiveThirtyEight Model Talk. Q: why only use regression and not machine or deep learning? More prevalent in 2018
1
Brice Morrison retweeted
Finn in 1989 is out now on iOS! Can you help Finn get home? #nostalgia #madewithfungus #madewithunity #indiegames itunes.apple.com/us/app/finn…
3
6
1
14