Nathaniel Tucker

I talk about #programming, #ReactJS, #TypeScript, #Tesla, and gamer culture.

[Nathaniel Tucker @npinp]

Happy 250 years

[Nathaniel Tucker @npinp]

Relatable

[Garry Tan @garrytan]

Woke up early today to use Fable 5 but it’s not enabled yet 😫

[Nathaniel Tucker @npinp]

Abstractions beat instructions

[Nathaniel Tucker @npinp]

https://t.co/IQjLj6EBN4

[Lisan al Gaib @scaling01]

November 2025 changed everything for me

Claude 4 and GPT-5 weren't really amazing and my expectation was that we are likely in a slower timeline. But then Opus 4.5 came out.

Since then every new model and revenue report has just reinforced this new world-view that we are still early and everyone is constantly underestimating it

Predictions that were ridiculously bullish a year ago, 6 months ago or even 3 months ago were underestimates

If you want to call the top on the AI bubble, then go ahead, but to me this seems like shorting Moore's Law in 1970

As long as revenue and compute keeps growing it seems delusional to try to call a top

[Nathaniel Tucker @npinp]

https://t.co/Z4yuKxP9Id AI Models come up with really good marketing campaigns now

[Reactive Data Client @dataclientio]

https://t.co/dqsuXvmj1N normalized data brings up to 93x performance over react fetch frameworks like react query

[TypeScript @typescript]

TypeScript 6.0 is now available!

This release brings better type-checking for methods, new standard library features, new module features for Node.js, and more!

But most important, this release brings us one step closer to the upcoming native-speed 7.0!

https://t.co/hon0RU1L5B

[PlanetScale @PlanetScale]

Introducing Database Traffic Control: a Postgres traffic management system built into PlanetScale.

Enforce flexible budgets on your database traffic to protect against unexpected and dangerous workloads.

[Nathaniel Tucker @npinp]

2025 was the year agents became a thing. 2026 is where the impact starts to become tangible. Real productivity boosts coupled with price drops and layoffs. 2027 will only accelerate this trend as the impact spreads to slower-adopting industries.

[François Chollet @fchollet]

Sufficiently advanced agentic coding is essentially machine learning: the engineer sets up the optimization goal as well as some constraints on the search space (the spec and its tests), then an optimization process (coding agents) iterates until the goal is reached.

The result is a blackbox model (the generated codebase): an artifact that performs the task, that you deploy without ever inspecting its internal logic, just as we ignore individual weights in a neural network.

This implies that all classic issues encountered in ML will soon become problems for agentic coding: overfitting to the spec, Clever Hans shortcuts that don't generalize outside the tests, data leakage, concept drift, etc.

I would also ask: what will be the Keras of agentic coding? What will be the optimal set of high-level abstractions that allow humans to steer codebase 'training' with minimal cognitive overhead?

[Nathaniel Tucker @npinp]

LLMs are just the new cpu architecture like x86 or ARM

[Nathaniel Tucker @npinp]

Cursor currently has agent, plan, debug, ask. They need to add eval. This will help refine skill generation by generating synthetic test sets, etc.

[Nathaniel Tucker @npinp]

Specializations are dead. Long live AI

[Nathaniel Tucker @npinp]

https://t.co/dkdY4MaTAv
At the same non-MFG framerate, nvidia GPUs are always lower latency than AMD - even with MFG applied.

[Reactive Data Client @dataclientio]

https://t.co/h5OhwJikEU

Vue 3 support!

[Nathaniel Tucker @npinp]

https://t.co/VA2tDJPNfY

[Nathaniel Tucker @npinp]

https://t.co/Kjsjtr726u

[Nathaniel Tucker @npinp]

Surely the 32billion in quarterly profit is fake. Its just an accounting trick of taking money in exchange for goods

[Nathaniel Tucker @npinp]

@stackblitz ...how? it shows `node -v
v18.20.3`