OpenAI Researcher: 100% of Code Handed Over to AI, Claude Rewrites Python Library

marsbitPublished on 2026-08-17Last updated on 2026-08-17

Abstract

OpenAI researchers and prominent developers like DHH (creator of Ruby on Rails) are reporting a dramatic shift toward AI-driven coding, with some claiming they no longer write code manually. DHH recently used Claude Fable 5 to fully rewrite the Python library "TerminalTextEffects" into Rust in a single, largely unassisted session, consuming 110 million tokens. The resulting Rust executable is only 3MB, with startup time slashed from 87ms to 2ms and a 9.6x render speed increase. This follows DHH's own reversal from a year ago, when he opposed ceding coding to AI, fearing the loss of "muscle memory" and deep learning. Now, he predicts that within five years, few people will be writing or reading code directly. The article highlights other large-scale migrations, like Bun's move from Zig to Rust in under two weeks, suggesting the marginal cost of code generation is nearing zero. The future role of programmers is envisioned as shifting from writing code to defining requirements, designing constraints, establishing test frameworks, and validating AI output—focusing on discerning "what is worth building" and "what is correct."

Claude Code's creator has publicly stated that he hasn't handwritten a single line of code in over two months.

In a single day, he can merge 27 PRs, all handled by Claude.

OpenAI researcher roon was even more extreme: 'I don't write code anymore; 100% is done by GPT.'

Now, another big name, after deeply experiencing Claude Code and Codex, declared, 'In five years, humans won't write code anymore!'

These past few days, Rails creator DHH personally took on a major task—

Using only Claude Fable 5, he completely rewrote the Python library 'TerminalTextEffects' into Rust in one go.

What's astonishing is that this refactoring consumed a staggering 11 million tokens, almost completing it in a single pass.

The results after it ran were nothing short of 'cheating'—startup time was compressed from 87 milliseconds to just 2 milliseconds, and rendering speed skyrocketed by 9.6 times.

The post instantly garnered millions of views across the internet.

One AI expert directly posed a soul-searching question to the Rails creator: 'If that's the case, where does Ruby go in the next five years?'

DHH's answer was straightforward—

Within five years, not many people will be writing or reading code by hand anymore. So, it really doesn't matter.

Who would have thought that in just one year, the contrast would be so stark!

Handing the Keyboard to AI, Rather Retire

Remember, in May of last year, DHH was firmly stating online that he refused to cede the joy of coding to AI.

In that lengthy post 'Coding should be a vibe!', he clearly stated:

AI is, at best, an assistive 'pair programmer,' good for looking up APIs and answering questions.

He even issued a stern warning: 'If the day comes when I must completely hand the keyboard over to AI, I would rather retire.'

I have zero interest in giving up coding. It's not some chore to offload to AI. What would be the point? To become a project manager for a pack of AI 'hooligans'?

In that six-hour deep-dive conversation with Lex Fridman, DHH insisted that every line of his code was typed by his own hands.

Once, while building a Linux distribution, he repeatedly asked AI to generate the same Bash conditional statement, only to realize that because he lacked the physical act of typing, he never truly mastered it.

This loss of 'muscle memory' left him deeply unsettled. 'Is this the end of learning?'

However, by April this year, the winds had shifted dramatically.

On a podcast, he admitted he had now fully switched to 'Agent-first,' essentially saying goodbye to handwritten code.

Yet, no one expected the phrase 'in five years, not many people will be reading or writing code' to come from the mouth of the Rails creator.

Fable 5 All-in, No One Writes Code in Five Years

Let's take a closer look at this hardcore Python rewrite by Claude.

TerminalTextEffects, or TTE for short, is a terminal visual effects engine.

It can be used both as a command-line program and imported as a Python library into other applications.

Developers can, like magicians, control text trajectories, colors, gradient effects, and animation sequences, transforming dull UIs into something cool.

The Rust version demonstrated by DHH can run 37 effects.

A piece of software that originally required a Python runtime environment was transformed by Claude's refactoring into a mere 3MB executable.

This new repository is called ttfx, hosted under DHH's own Omarchy organization, with every commit history intact.

The entire process took 3 hours and 11 minutes. The main Rust code is 21,000 lines, almost the same volume as the original Python version.

During the task, 8 Agents each worked on a separate branch simultaneously, in batches: reading the code themselves, generating implementations, compiling, running tests, handling failures, then moving to the next round.

The so-called 'one-shot' was essentially handing the task over once.

Using the same method, DHH had Codex complete it, and the results after a single prompt were also excellent.

However, it was 30% slower and cost $43 (290 RMB) in Tokens.

DHH's hardcore operation directly blew up the community, drawing out several Anthropic bigwigs.

Claude Code creator Boris Cherny couldn't help but appear in the comments exclaiming, 'This is insane!'

Faced with a follow-up question from another researcher, Thariq, DHH revealed an even more astonishing detail—

He simply asked Claude to formulate a plan. After that, it was zero intervention throughout, no complex workflows applied, no specific goals pre-set; it was all about complete delegation of authority.

Million-Line Codebase, Bun One-Click Migration

TerminalTextEffects, after all, is limited in scale.

What truly demonstrates the power of AI coding is a massive refactoring in Bun's core.

A few months ago, founder Jarred Sumner personally spearheaded the migration of the massive codebase from Zig to Rust in its entirety.

It's astonishing that this monumental project, involving a million lines of code, was declared 'complete' in less than two weeks.

If this were a few years ago, a project of this magnitude would have been a marathon lasting several quarters, if not years.

Future Coders to Become 'Dragon Tamers'

Now, all signs are frantically hinting at a fact that is both brutal and exciting—

The marginal cost of code generation is approaching zero.

This inevitably plunges many into panic. 'If no one reads or writes code in five years, will programmers disappear?'

Actually, 'no one writes code' absolutely does not equal 'programmers disappear.'

The core work of future programmers will undergo a fundamental shift—

From 'personally implementing code' to fully focusing on defining requirements, designing constraints, establishing testing frameworks, and judging whether the AI wrote it correctly.

It's foreseeable that when 'handcrafting code' becomes history, the only remaining scarce moats will be two points:

Insight into 'what is worth doing' + defining 'what counts as correct.'

Rather than worrying about losing your keyboard, it's better to start thinking now: what kind of Rome do you want to command this boundless-compute 'super coder' AI to build?

References:

https://x.com/dhh/status/2086713611934695848?s=20

https://claude.ai/code/artifact/287825bc-7aad-4541-a7e7-fa4ba8d03612

This article is from the WeChat public account "New Zhiyuan", author: Taozi

Related Questions

QWhat major transformation did DHH perform using Claude Fable 5?

AHe completely rewrote the Python library 'TerminalTextEffects' into Rust in one go.

QWhat were the performance improvements after the AI-assisted rewrite of TerminalTextEffects?

AStartup time was reduced from 87 milliseconds to just 2 milliseconds, and rendering speed increased by 9.6 times.

QAccording to DHH, what will happen to human coding in the next five years?

AVery few people will be hand-writing or reading code anymore, as the focus will shift to other tasks.

QWhat significant project did Bun founder Jarred Sumner undertake with AI assistance?

AHe migrated the entire massive codebase of Bun from Zig to Rust in less than two weeks.

QWhat does the article suggest will be the core role of future programmers in the age of AI coding?

ATheir core role will shift from writing code to defining requirements, designing constraints, establishing testing systems, and judging whether the AI's output is correct.

Related Reads

Deciphering TapeOut: A Child Built a CPU On-Chain

**Title: Understanding TapeOut: A Kid Built a CPU On-Chain** **Summary:** The article explores a remarkable experiment where a young developer named Blonskr has used blockchain technology to build a functional, on-chain CPU. Named "Behemoth," this CPU is based on the 1971 Intel 4004 processor specification. It runs on the BNB Chain, uses block production as its clock (running at a glacial 2.22 Hz), and is perhaps the slowest CPU in existence, yet it represents a novel and intriguing concept in the on-chain space. The core concept is the TapeOut protocol, named after the final "tape out" stage in semiconductor manufacturing. It treats the blockchain as a silicon wafer, with tokens representing fundamental logic components. The protocol's atomic unit is an ERC-1155 token representing a single NAND gate, the fundamental building block of digital logic. Users can visually design circuits on a "canvas," connecting these logic tokens. Once a design is finalized, the underlying tokens are burned, and an ERC-721 NFT representing the permanent, immutable circuit is minted. Blonskr used 2,300 such tokenized NAND gates to construct the Behemoth CPU. Key features of this and any TapeOut circuit include **permanent operation** (running as long as the chain exists), **free, permissionless evaluation** (anyone can query it without gas), and **safe composability** (circuits cannot call external contracts or modify state, making them inherently safe to use). This enables a new form of open, collaborative hardware design, where anyone can build upon and integrate components created by others. While highly niche, TapeOut reimagines the foundations of computation using blockchain's properties of permanence and openness. It pushes the boundaries of what can be built on-chain, potentially enabling future applications like custom mining circuits or decentralized, specialized processors. The experiment demonstrates an exciting combination of extreme technical vision and creative curiosity.

marsbit33m ago

Deciphering TapeOut: A Child Built a CPU On-Chain

marsbit33m ago

Novig Sues Wisconsin as Sports Prediction Market Dispute Heats Up

Novig, a sports event prediction market operator, has filed a lawsuit against Wisconsin's attorney general. The legal dispute centers on whether prediction markets fall under federal derivatives regulations or state gambling laws. The lawsuit, filed in a U.S. district court, seeks a declaratory judgment after Novig began offering event contracts to Wisconsin residents. This case is part of a broader conflict. In April, Wisconsin sued other prediction market platforms like Kalshi and Polymarket, alleging their sports-related contracts violate state gambling laws. Novig argues its contracts are "swaps" regulated exclusively by the federal Commodity Futures Trading Commission (CFTC), under the Commodity Exchange Act. Wisconsin contends they are sports betting. Federal courts have issued conflicting rulings on similar cases, creating legal uncertainty. The outcome is significant as prediction markets are a fast-growing sector, with trading volume reaching $9.5 billion on a single day in August. These markets are also increasingly intertwined with cryptocurrency infrastructure. Simultaneously, Novig is pursuing a nationwide legal strategy, having filed similar lawsuits in four other states. The company also recently secured a marketing partnership with the New York Mets, marking the first such deal with an MLB team. The Wisconsin case's resolution will influence whether prediction markets can operate as national financial products or remain constrained by individual state laws.

cryptonews.ru39m ago

Novig Sues Wisconsin as Sports Prediction Market Dispute Heats Up

cryptonews.ru39m ago

Держатели XRP могут торговать опционами на платформе Derive, используя FXRP в качестве залога

XRP holders can now trade options on the Derive platform using FXRP as collateral, as announced by Flare on August 12. This integration allows users to open positions from self-custody wallets while the underlying XRP backing the FXRP remains on the XRP Ledger. According to DeFi analyst Will Procheska, this provides XRP's dedicated holder base with a permissionless options market for generating yield or hedging. Derive's platform combines protocol-level settlements with an order book managed by Derive Trading Co., enabling users to retain asset control while professional market-makers provide liquidity. XRP options on Derive are cash-settled in USDC, so profits or obligations adjust the trader's USDC balance without transferring XRP or FXRP. The platform's portfolio margin system assesses overall account risk but may still trigger liquidations if margin levels fall below requirements. The launch expands Flare's XRPFi ecosystem. FXRP, introduced via the FAssets system in September 2025, creates an on-chain representation of XRP for use in smart contracts. It has since been integrated into spot trading and, more recently, permissionless lending markets on Morpho. This addition of options on Derive offers XRP holders hedging and premium-earning capabilities comparable to other major assets. While regulated XRP options debuted on CME Group in October 2025, Derive provides a decentralized alternative with USDC settlement and direct wallet access. The platform also supports perpetual futures, offering further trading strategies. Flare and Derive are exploring automated "strategy vaults" to simplify yield-generating options approaches for users.

cryptonews.ru40m ago

Держатели XRP могут торговать опционами на платформе Derive, используя FXRP в качестве залога

cryptonews.ru40m ago

Trading

Spot
活动图片