Yasith Ariyasena

Evanescence is life.

[Yasith Ariyasena @YasithEv]

Finally got this beautiful piece by @Kelly_McKernan framed! @evanescence

[Evanescence @evanescence]

Our 6th studio album “Sanctuary” is out now, anywhere you listen to music! Thank you to all of the brilliant, creative people who contributed to this collection of songs we are so very proud of. May it feed your soul.

Stream: https://t.co/oc7mpopLPm
Shop: https://t.co/iTLwbtRTMu

[Gergely Orosz @GergelyOrosz]

That feeling of: "I'm in the middle of the code... oh, this is such a nasty hack. OK, let me clean it up as I go. [2 hours pass] OK, it's done, now let me get back to where I was."

It just never happens as organically as I use AI agents. I no longer spot stuff as I don't "live in" the code...

[Evanescence @evanescence]

We are so incredibly excited to announce our new album, Sanctuary. It’ll be available on streaming platforms on June 5th. Presave live now. Our new single, Who Will You Follow, is out TONIGHT AT MIDNIGHT!! This album is over three years in the making, and we are so damn proud of every second of it. Hope you love it and can’t wait for you to hear it! HERE WE GO!!!

https://t.co/EAFo4Ujw9K

Style by: Marjan Malakpour & @Gelarehdesigns
Photographer: Chapman Baehler

[Yasith Ariyasena @YasithEv]

@cirnosad As a Sri Lankan 🇱🇰 I oppose the Brown point 😅

[Klaas @forgebitz]

ironically the first thing ai killed was no-code

everyone is now coding

[shaurya @shauseth]

startup idea: we sell hand made artisanal code

[Served with Andy Roddick @Served_Podcast]

This just in: man regrets inspiring child

[Yasith Ariyasena @YasithEv]

@h_liyan @SampathBankPLC The new web app is such a great use case of trying to change something that's not broken, and losing all the stability and reliability the old one had.

[Google for Developers @googledevs]

console.log("here") is valid debugging. We don’t judge.

[Yasith Ariyasena @YasithEv]

"It hurts the ego a bit" - exactly the struggle I'm having right now. 😅

[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.

[Yasith Ariyasena @YasithEv]

@AsithH 😍

[Ajay Kulkarni @acoustik]

Yet Postgres continues to conquer all. It's conquered time-series. It's conquered geospatial. And most recently it's conquered vector.

That's because most people don't need specialized databases. Simplicity is a virtue. Premature optimization is the root of all (programming) evil.

[Yasith Ariyasena @YasithEv]

Can @zeddotdev do the same thing they did to IDEs to browsers as well? 🤞🤞

[Yasith Ariyasena @YasithEv]

@ghostamanita

[Yasith Ariyasena @YasithEv]

Ella, Sri Lanka. @evanescence

[Yasith Ariyasena @YasithEv]

The mother, the daughter and the holy roller really lived up to the hype🤘🤘🤘

[Sumerian Records 🇺🇸 @SumerianRecords]

'End of You' by Poppy, Amy Lee and Courtney LaPlante is out now everywhere.

Watch the official music video now on the Sumerian Records YouTube channel.
https://t.co/bf4U66sEUl

[ThePrimeagen @ThePrimeagen]

everyone has a plan until you ship to prod

[Yasith Ariyasena @YasithEv]

Don't think the way he says "Potter" gets any better! Class all round!

[Variety @Variety]

Tom Felton says the controversy around J.K. Rowling's political views doesn't impact him: "I'm not really that attuned to it...I have not seen anything bring the world together more than Potter. She's responsible for that, so I'm incredibly grateful." #TonyAwards

[Yasith Ariyasena @YasithEv]

So @Azure decided to break their existing managed Postgres APIs silently and reduced the db name char length to 31 from 63, breaking all our existing integrations overnight. Funnily their docs still say the max char length is 63! Talk about being a shitty cloud provider! 🤮

[Yasith Ariyasena @YasithEv]

Been using @zeddotdev for the last 3 weeks, and it keeps giving all the good reasons not to go back 🚀

[Zed @zeddotdev]

The world's fastest AI code editor is here
Zed is engineered from scratch in Rust like a video game. Not another fork, but a purpose-built editor designed for collaboration between humans and AI, delivering a lightning fast agentic editing experience.

https://t.co/dPumqwS4ls