Chinthaka Chandrasekara

Software Architect | Sports Writer | Casual Gamer

[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.

[ARC Raiders @ARCRaidersGame]

📡 The Riven Tides Update is out now!

Explore the abandoned shoreline, traverse the Exodus port, and experience the lost luxury of the Panorama Azzurro hotel. This isn’t a holiday by the beach, it’s the Rust Belt - it’s not going to be easy.

Other Raiders are already on the scent of fresh loot, and a dangerous new ARC enemy has been seen patrolling the skies by the shore.
Check out the blog, and head to the coast! -
https://t.co/oFApBHS8qm

[ARC Raiders @ARCRaidersGame]

📡 Eyes to the skies, Raiders, The Flashpoint update is now live!
Speranza is alive with speculation swirling around a new ARC Operation, evolving enemy threats, and unexplained aerial phenomena. Gear up with Tian Wen’s new arsenal, and get to work on the new antenna project - danger lurks on the horizon.

Check the full patch notes here!
https://t.co/qpFFvpxXIa

[ARC Raiders @ARCRaidersGame]

📡 Attention, Raiders!
The Shrouded Sky Update is live! ⛈️
Violent hurricanes are sweeping topside, forcing new strategies for low-visibility combat.
Scouts have spotted two new ARC types in the Rust Belt; we advise caution while the storm runs its course, but those who know how to read the weather will find opportunity in the chaos.
Read the patch notes here:
https://t.co/aOmp5yWVJo

[ARC Raiders @ARCRaidersGame]

📡 The Headwinds update is now live!
Take on the ARC and scrap them for trophies to display back home, cautiously plot your way though 1V3 encounters, and keep an eye on the Buried City rooftops for bird nests hiding precious trinkets.
Ready to go up against the odds, Raider?
Check out the patch notes here -
https://t.co/D8ix5qnM5y

[ARC Raiders @ARCRaidersGame]

📡 Attention, Raiders!
We survived the Cold Snap, but don't drop your guard.
Topside is changing - extreme weather ravages the surface while ARC numbers are climbing.
Lock your loadout, the scale of the impending escalation remains unknown...
https://t.co/SJ8k0apSvM

[ARC Raiders @ARCRaidersGame]

📡 Welcome to the Rust Belt.
Deadly ARC machines roam the surface as the last of humanity fight over valuable supplies.
Loot is scarce, death is quick.
Do YOU have what it takes to become a Raider?
Enlist. Resist.

[ICC @ICC]

Multiple spin bowling outlets in Australia's provisional squad for the #T20WorldCup 🌪️

More ➡️ https://t.co/d0WnqZauc7

[ICC @ICC]

A familiar core shapes England’s provisional 15 for the Men's #T20WorldCup 👌

Read more ➡️ https://t.co/hZp9Tcqp0l

[ICC @ICC]

Rashid Khan will be at the helm for Afghanistan at the #T20WorldCup 👌

More on the squad 👉 https://t.co/zBZO20AJXv

[ICC @ICC]

Oman's leading T20I run-getter Jatinder Singh is set to lead the 15-member squad for the #T20WorldCup 💪

More ➡️ https://t.co/uBdNOV7huf

[ICC @ICC]

Australia name their side on a quest to claim Ashes series honours in Adelaide 👊

More 📲 https://t.co/IbUkvqKO20

#AUSvENG #WTC27

[ICC @ICC]

Josh Tongue 🔁 Gus Atkinson

With the Ashes on the line, England make one change to their Playing XI for the crucial Adelaide Test 👊

#WTC27 | #AUSvENG | Read more 👉 https://t.co/PKXMRepeEX

[StarLadder CS2 @StarLadder_CS]

Eight teams are entering the arena.
Only one can leave as champions.
#BudapestMajor

[Formula 1 @F1]

THE STARTING GRID FOR THE SEASON FINALE 👀

#F1 #AbuDhabiGP

[StarLadder CS2 @StarLadder_CS]

🆚 Here’s your guide to where the teams stand in Stage 1 brackets of the #StarLadder #BudapestMajor!

The first battles in Swiss format await the 16 mighty teams. Which 8 can dominate this Stage and advance?

📺 Catch every play of Stage 1 LIVE from November 24-27.

[StarLadder CS2 @StarLadder_CS]

Meet the ever-so-lovely talent lineup for the StarLadder Budapest Major 2025!

But wait, we might have a few more surprises in store! Stay tuned for our special guests!👀

[Everpower Labs @EverpowerLabs]

A new forge is opening.
Where ideas turn into full #Evernode smart contracts… and deploy to an Evernode cluster in a single flow.
#EverForge — the next evolution of @EvernodeXRPL development.

This is what EverPower Labs has been shaping these days.

[Mufaddal Vohra @mufaddal_vohra]

MARK WOOD’S 2ND OVER:

151.1kmph.
150.9kmph.
150kmph.
151.5kmph.
148.7kmph.
150.6kmph.
150.3kmph.

[England Cricket @englandcricket]

That... was crazy 😅

🏏 Runs: 295
☝️ Wickets: 19

What a way to kick-start the series! 🔥