Kushagra Mathur

Software Engineer | AI Builder
Turning ideas into products with code.
Sharing code, system design & career insights

[Kushagra Mathur @CoderGhost37]

@adxtyahq bro is 21 and already done 😭 relax, you've got time

[Kushagra Mathur @CoderGhost37]

@milan_milanovic 63% of the code but teams still judge devs on how much they ship. no wonder only 23% feel better about it

[Kushagra Mathur @CoderGhost37]

@ChShersh kinda? dsa has one right answer. system design is mostly arguing about tradeoffs with half the requirements missing lol

[Kushagra Mathur @CoderGhost37]

@Hiteshdotcom Labs with AI built in is the right shape for learning now. Breaking a real container and working out why teaches system design faster than any diagram

[Kushagra Mathur @CoderGhost37]

@theo Nightly users are great QA until they become the loudest voice in your feedback. Their bugs are real, but their priorities aren't your typical user's

[Kushagra Mathur @CoderGhost37]

@GergelyOrosz Hiring managers look up your handle before the interview. Disagree hard with the idea, never with the person, and it actually helps your career

[Kushagra Mathur @CoderGhost37]

@piyushgarg_dev One real user teaches you what 100 tutorials can't: weird inputs, slow pages, the feature nobody touches. That feedback loop is the actual resume

[Kushagra Mathur @CoderGhost37]

@theo Cutting a feature power users rely on just to "simplify" is what happens when a team optimizes for dashboards instead of the people using the product

[Kushagra Mathur @CoderGhost37]

@piyushgarg_dev The real comparison isn't speed per token, it's deciding what's worth building.
Models write the code now, picking the right problem is still the expensive part

[Kushagra Mathur @CoderGhost37]

Opus 5.5 week made one thing obvious: writing code isn't the scarce skill anymore.

Deciding what to build, writing a spec an agent can't misread, and knowing which tradeoffs matter at scale is the job now.

[Kushagra Mathur @CoderGhost37]

@theo At this point the ceiling usually isn't the model, it's how clearly you can describe what you actually want built. Spec quality is the new bottleneck

[Kushagra Mathur @CoderGhost37]

@theo Option 3: Microsoft never really ports the debt and just ships a translation layer good enough that nobody notices. That's what made Apple's switch work, not the porting

[Kushagra Mathur @CoderGhost37]

@theo Design cleanup is the most underrated performance upgrade. Same features, less friction, and the app suddenly feels faster

[Kushagra Mathur @CoderGhost37]

@Suryanshti777 Both are true because writing code was never the bottleneck. Vibe-coded apps don't break on syntax, they break on a fuzzy spec and a data model nobody thought through

[Kushagra Mathur @CoderGhost37]

@pauliusztin_ Harness over model is the most underrated take right now. With the same model, better context management and tool design move output up a whole tier

[Kushagra Mathur @CoderGhost37]

@arpit_bhayani Fine by me. Typing code was never the bottleneck.
Deciding what to build, what to cut and which tradeoffs you can live with in prod still is

[Kushagra Mathur @CoderGhost37]

@theo Speed is the most underrated feature in dev tools. Every extra second of waiting is an invitation to switch tabs and lose the thread

[Kushagra Mathur @CoderGhost37]

@mehulmpt The routing layer is the easy half. The hard half is keeping prompts and output formats portable, so failing over doesn't quietly change behavior

[Kushagra Mathur @CoderGhost37]

@sakatayasha Finish time matters less than how many follow-up prompts it took to get the puzzle working.
One-shot comparisons hide the iteration cost.

[Kushagra Mathur @CoderGhost37]

@bindureddy Cheap and fast on easy tasks is where most production traffic actually lives. The real design move is routing: send the boring 80% to Flash and only escalate to a frontier model when the task needs it