Kangkan Boro

5.6K posts

Kangkan Boro banner
Kangkan Boro

Kangkan Boro

@kangkanB

AI @ borderplus, Previously GenAI platforms @fractalai Startup chaos veteran Arsenal fan with a GPU addiction

🌎 Katılım Mayıs 2009
1.7K Takip Edilen296 Takipçiler
Kangkan Boro retweetledi
Nick Khami
Nick Khami@skeptrune·
>what do you think of the claude codebase? brother, i'm not even reading my own code anymore. what makes you think i'm going to read someone else's?
Nick Khami tweet media
English
97
498
6.5K
167.6K
Kangkan Boro retweetledi
Claude
Claude@claudeai·
Computer use is now in Claude Code. Claude can open your apps, click through your UI, and test what it built, right from the CLI. Now in research preview on Pro and Max plans.
English
2.6K
4.9K
59.4K
15.8M
Kangkan Boro retweetledi
shadcn
shadcn@shadcn·
git worktree is a great feature for people smarter than me
English
154
146
3.9K
198.1K
Kangkan Boro retweetledi
aditya
aditya@adxtyahq·
Me and the API key I hardcoded “just for testing”.
English
63
565
10.4K
369.6K
Kangkan Boro retweetledi
Andrej Karpathy
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.
English
1.6K
5.4K
39.4K
7.6M
Kangkan Boro
Kangkan Boro@kangkanB·
@MyIndusIndBank applied for the IndusInd Avios CC January 1st week and have not received the card yet. Today I get an SMS saying that my bill has been generated - 11800 annual fee but I DONT HAVE THE CARD YET. I do not want this card anymore, please cancel it .. you’re wasting 🕣
English
1
0
1
203
Kangkan Boro retweetledi
gaut
gaut@0xgaut·
realizing you don’t need to know how to code to build good ideas anymore but you have no good ideas
English
214
488
8.2K
405.9K
Kangkan Boro retweetledi
Dan Robinson
Dan Robinson@danrobinson·
Claude Code is humbling in how fast it can prove that my cool backlog ideas that I never had the time to implement were actually pretty mid
English
107
206
5.9K
214.5K
Kangkan Boro
Kangkan Boro@kangkanB·
@bcherny Was just thinking about this yesterday and you shipped this today. Thank you!!
English
0
0
0
15
Boris Cherny
Boris Cherny@bcherny·
A small quality of life detail: you can now press tab to add more instructions when accepting/rejecting a permission prompt. We tried probably a dozen iterations of this UX over the last few weeks before deciding to ship this one. Let us know what you think!
English
427
260
5.7K
351.7K
Kangkan Boro retweetledi
Reid Hoffman
Reid Hoffman@reidhoffman·
I Am Voicepilled. A major step forward in human–computer interaction won’t come from bigger models alone, but from how we talk to them, natively, with our voices. More thoughts:
English
101
126
931
281.3K
Kangkan Boro retweetledi
Gergely Orosz
Gergely Orosz@GergelyOrosz·
Gartner has been out of touch with tech analysis: and their latest report on AI coding assistants show just by how much. - They rank Amazon, GitLab, GCP, Windsurf all above Cursor - No mention of Claude Code or OpenAI Codex Cursor pays Gartner nothing: others do Embarrassing
Gergely Orosz tweet media
English
128
129
1.5K
344K
Kangkan Boro retweetledi
vas
vas@vasuman·
mr. beast says he plans to take 100 software engineers and lock them in a room with no Cursor subscription, with the first person to ship something that compiles taking home $1 million
vas tweet mediavas tweet media
English
490
451
14K
904.6K