Umut

1.1K posts

Umut banner
Umut

Umut

@thisismutty

Founder @ https://t.co/K4eoZ0hHK3. Building products for the built world.

London Beigetreten Kasım 2022
2.6K Folgt143 Follower
Angehefteter Tweet
Umut
Umut@thisismutty·
🚨 AI Learning App has reached Beta stage! Introducing Zazu Beak — Learn Languages Like a Local 🦜 👇 Here's how it all started... 👇 #LanguageLearning #AI #buildinpublic #kinda
English
1
0
2
475
Dara
Dara@offpaths·
I Left my job and life in the uk. I’m betting on myself. 2026 is the year to build my business with my best friends, shipping, and experiences with new people. I’m going to post and document everything through my videos on X. @robj3d3 and @levelsio, thanks for the motivation to push myself out of my comfort zone. It’s going to be lit!
English
245
53
1.2K
170.3K
Andre
Andre@Youkhna·
I got tired of juggling Notion, Slack, Gmail, iMessage, Linear. So I built attn. One feed. One flow.
Andre tweet media
English
53
13
990
259K
Umut
Umut@thisismutty·
@yongfook You’ve been around too long, old man. 😅😂
English
0
0
0
9
Jon Yongfook
Jon Yongfook@yongfook·
2000 - Rails etc: "Building is not the hard part now. Marketing is" 2010 - React / Vue etc: "Building is not the hard part now. Marketing is" 2020 - Nocode: "Building is not the hard part now. Marketing is" 2026 - Claude etc: "Building is not the hard part now. Marketing is"
English
135
108
1.8K
261.2K
James Gillespie
James Gillespie@JamesGillespieX·
@fashiongiik @t_blom @ryan_t_brown I think even if you were to improve the datasets, it still wouldn't be enough. It may even be that AGI is a prerequisite for making an agentic, artistically creative AI.
English
3
1
1
231
Andres Hernandez
Andres Hernandez@cybereality·
@samwhoo This is a duplicate tweet. Please see these 2 other tweets that have nothing to do with your post. Also, your use of "holy shit" is against our community guidelines, and you've been banned.
English
30
17
1.6K
68K
Sam Rose
Sam Rose@samwhoo·
StackOverflow graph of questions asked per month. Holy shit.
Sam Rose tweet media
English
870
1.9K
27.8K
4.7M
Umut
Umut@thisismutty·
@flybayer So what you’re saying is, you are the bottleneck? 😉
English
1
0
1
33
Brandon 🚀 Flightcontrol
For really complex work, AI writes thousands of lines of working code within an hour But then I spend 1-3 days to fully understand, prompt deep refactors, improve end user UX, and ensure all edge cases are working and tested. That’s even after crafting a long, detailed plan document at the start. Because with complex stuff, you can’t foresee and address everything up front. A lot of times this is foundational stuff that is critical to get right in order to not cripple your future self.
English
30
6
157
21.4K
Umut
Umut@thisismutty·
> This whole thing is just a really big learning experience for me, and I'm really enjoying it. Build, fail forward, and keep shipping. Basically what it boils down to. Excellent read.
Ben Tossell@bentossell

x.com/i/article/2006…

English
0
0
2
40
Jaytel
Jaytel@Jaytel·
For building our EOY reel, I used to open After Effects. This time, I opened Cursor. We built a hyper-specific Mac app to sequence all the clips: - Random reshuffling to try different orders - Transforms + background color fill - Global clip-length adjustment - Visual thumbnail timeline That kind of shuffling + global tweaking + visual grid just isn’t possible in another tool.
Marvin Schwaibold@MSchwaibold

Last day of school 2025 👋

English
52
34
761
136.7K
dax
dax@thdxr·
ship something shitty fast and fix it later culture just does not produce anything great there's mountains of rationale as to why you should do that but i've never seen it work and it always turns the company into a painful place to work nothing going on right now changes this
English
115
73
1.4K
67.7K
Umut
Umut@thisismutty·
@jarrodwatts Having AI interview you is the best technique for most tasks that require that authentic touch. Really good for blog posts or any post for that matter.
English
0
0
0
24
Jarrod Watts
Jarrod Watts@jarrodwatts·
This is an excellent prompt. Slop is a result of AI misinterpreting what you're asking - a skill issue from the user. By repeatedly narrowing down the task to be more specific, you remove the potential for misinterpretations to occur, and end up with far better results.
Thariq@trq212

my favorite way to use Claude Code to build large features is spec based start with a minimal spec or prompt and ask Claude to interview you using the AskUserQuestionTool then make a new session to execute the spec

English
20
42
722
93.6K
Umut
Umut@thisismutty·
@mitsuhiko 10 for github copilot and you can get the same thing. These people need more than credits, they need workflows that they can retrace for themselves. It really does require a different perspective. And don’t ask me, I can’t be arsed.
English
0
0
1
320
Armin Ronacher ⇌
Armin Ronacher ⇌@mitsuhiko·
If you are a programmer and an AI hold-out, and you have some time off during Christmas: gift yourself a 100 USD subscription to Claude Code and … try it. But really try it. Take a week if you can afford it and dive in. It will change your opinion on these tools.
English
28
15
277
64.5K
Umut
Umut@thisismutty·
My feed is full of software engineer cope, and I love it.
English
0
0
0
5
Umut
Umut@thisismutty·
@anshnanda Stop acting like an engineer, start acting like a manager, then the game changes.
English
0
0
0
56
Dev Agrawal
Dev Agrawal@devagrawal09·
an unlikely trio appears
Dev Agrawal tweet media
English
19
18
1.3K
70.7K
Umut
Umut@thisismutty·
@svpino Code has always been a means to an end.
Umut tweet media
English
0
0
1
4
Santiago
Santiago@svpino·
Lately, I've gain a ton of respect for vibe-coders. We are here on our high horses, telling them how their code is shit and how models can't fix their messes, but they just don't care. Many of these folks are simply optimizing for a different outcome. For them, code is just a means to an end. They don't care about maintainability, elegance, or correctness because they aren't planning to touch the code. They care about shipping their idea before they forget. Do you know how many ideas I've had that I've never executed on because I didn't have the time or was too lazy to get off my couch? I can learn a thing or two from people willing to make things happen, even when so many aristocrats tell them they shouldn't.
English
274
83
1.4K
289.3K
Umut
Umut@thisismutty·
@Smooth_Runnings @haridigresses @practiklyperfct @0xHorseman I think you should take a step back & think about it a different way, you’ve just been promoted kind of way. When you’re a manager, you’re thinking about the outcome, not the nitty gritty. Once you let go, it becomes clear. Try one day without thinking about all the small details
English
0
0
1
12
hari raghavan
hari raghavan@haridigresses·
Corollary: this is the best possible time for semi-technical non-engineers to catch up. Over the last 3 months, I went from someone who was a "technical PM" to ridiculously proliferous at shipping massive amounts of (what appears to be) quality code. Systems thinking + domain expertise are now FAR more important than the syntax of individual lines of code. In fact... getting caught up in the lines of code might actually be a hinderance. For context: I learned C++ in high school, then I was an Excel-monkey in my consulting days (but building complex models over 10-20 weeks that were basically data applications). I forgot any form of syntax over the last 20 years but the other experiences meant I built strong foundations in object-oriented programming, proper abstractions, systems thinking, and data structures. And I've spent most of my career in Finance, Biz Ops, Legal, HR... which means that I can be monstrously productive in building software for corporate finance teams. How productive? 500k+ LoC touched and hundreds of commits, in 11 weeks. Yes, yes, I know lines of code is not a KPI to optimize, but someone going from 0 to that order of magnitude should still paint a picture. And this isn't slop. It's reviewed by actual engineers on the team, and we're rigorous about PR reviews (in the earlier days I had to redo PRs from scratch many, many times because it wasn't good enough). The overall process works beautifully, because I have the multi-year product roadmap and the codebase architecture in my head. I'm able to consider future needs, and execute on a months-long roadmaps... in days. I genuinely feel like I just got access to a video game I've been yearning to play, for a long time... and somehow my copy came with God mode baked in. (This is funny because Andrej Karpathy is actually a god in this space and I'm probably just getting used to the power of building software, and just a teeny bit of Dunning-Kruger to boot...) But still. I share this because I chatted a few days ago with a close friend who's a really sharp systems thinker but not an engineer, who said "I feel like I missed the wave, it's too late for me to pick up vibecoding." I told him that I only began working in our codebase in earnest in early October. That things are changing so fast that those who previously learned to code are having to sprint really hard to keep up, too. That knowing the line-by-line syntax isn't the most critical for *most* products. That the game is changing every week... but that's a huge gift people like us, because it gives us a place to stand in order to move the world. And most of all, that if you're a systems thinker, have good taste in UI/UX, have domain expertise, and — I think this is somewhat important — that you love software... there is absolutely nothing stopping you from building something amazing. I *love* software. I thought several times about taking a detour to learn how to code, but life just never slowed down enough. Ironically, it was the practice of coding speeding up that gave me the opportunity to get on board. However long this lasts, I feel so fortunate to be able to actually get in there, and build something that I love.
hari raghavan tweet mediahari raghavan tweet media
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.

English
34
30
580
91.1K