Arthur Khachatryan

Sr. Front-End Engineer @ebay platform - css, js, responsive web, #ux interaction certified, #a11y advocate, seo expert, consultant, writer, and all things tech.

[Arthur Khachatryan @arthurk55]

Introducing my new Chrome extension to help reduce page reload times for #webdev https://t.co/qTZ3fpMMBb #javascript #CSS

[Claude @claudeai]

Introducing Claude Tag, a new way for teams to work with Claude.

In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while you focus on other work.

[Arthur Khachatryan @arthurk55]

📢 @AnthropicAI dropped support for the use of its models inside #OpenClaw and other harnesses. What does this mean for the future of third-party harnesses, Anthropic's leverage of its own platform? #AI #ClaudeCode #softwareengineering https://t.co/0t9Wz2fd9V

[Thariq @trq212]

CC Livestream https://t.co/BVCXUiJXxS

[Arthur Khachatryan @arthurk55]

@sonofalli Fantastic article!! I love the point about 'vibe coding' being less about laziness and more about 'product intuition.'
You imply that 'vibe coding' eventually eats the 'Systems' phase too. Will we have agents that self-correct their Order of Operations without human intervention?

[Arthur Khachatryan @arthurk55]

Metrics should reveal reality, not manufacture comfort.

If a number can improve while the real problem stays the same, the metric is measuring activity, not outcomes.

Good metrics illuminate progress.
Bad ones create theater. #Leadership #ProductManagment

[Arthur Khachatryan @arthurk55]

Assumptions work in small teams.
They break at scale.

Execution slows when definitions, decisions, and expectations live in people’s heads.

Clarity scales.
Assumptions don’t.

[Lisan al Gaib @scaling01]

https://t.co/G8mpPCub7a

[Arthur Khachatryan @arthurk55]

I Used Chrome DevTools MCP to Audit a Site — Here’s What It Found #UXDesign #AI #Chrome

https://t.co/ttJYAkKg5E

[Arthur Khachatryan @arthurk55]

Quality isn’t a final checkpoint.
It’s a system.

Late inspection can’t fix early ambiguity.
Define “done,” tighten feedback loops, and validate continuously.

You don’t test quality in.
You design it upstream.
#SoftwareEngineering #SoftwareDevelopment #QualityAssurance

[Arthur Khachatryan @arthurk55]

Roadmaps fail when they list activities instead of decisions.

Strong roadmaps clarify tradeoffs, surface assumptions, and tie work to outcomes.
Direction beats detail.

Clarity is the real alignment tool.

[Arthur Khachatryan @arthurk55]

Speed isn’t about working faster.
It’s about deciding earlier.

Delayed decisions preserve ambiguity, not flexibility.
Clear calls cut coordination, reduce rework, and unlock execution.

Hesitation is the real bottleneck.

[Arthur Khachatryan @arthurk55]

Many "complex #Frontend" problems aren’t about code.

They’re contract failures.

Unstable data shapes and unclear ownership force defensive logic.
Clear, versioned interfaces reduce regressions and speed iteration.

Stability beats cleverness in #SoftwareEngineering !

[Arthur Khachatryan @arthurk55]

@mattpocockuk I like the direction; docs-for-agents feels right, but skills aren’t docs. Once these become behavioral instructions, trust and injection risks start to matter. Also, how does an agent reliably know which package’s skill to load in large, fragmented dependency graphs?

[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.

[Arthur Khachatryan @arthurk55]

The #ux decision that moves metrics most isn’t polish or frameworks.

It’s constraint.

Too many valid paths increase decision load.
Hesitation rises.
Completion drops.

Senior #UXDesign means deciding which choices users should never have to make.

[Arthur Khachatryan @arthurk55]

@lydiahallie Thanks! I can't think of how best to formalize this into an automation workflow, but let me ask Claude. 😆

[Thariq @trq212]

https://t.co/eHD0AmjSRM

[Arthur Khachatryan @arthurk55]

Most sr. front-end bugs don’t look like bugs. They look like “clean code” - quietly ships the wrong outcome.

Problem: optimizing components before aligning on the user or business constraint. If you’re a senior dev and still optimizing in isolation, that’s the ceiling.

[Arthur Khachatryan @arthurk55]

Check out my latest article: Progressive Context Building: Why Your AI Should Get Smarter Every Time You Use It #js #react #ux #Accessibility https://t.co/MRQGibaodz

[Arthur Khachatryan @arthurk55]

Perplexity’s Unsolicited Bid For Chrome Is A Distribution Play

Read about it in @ARKInvest's newsletter! https://t.co/Tg45fM6h3R