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

marsbitPubblicato 2026-08-17Pubblicato ultima volta 2026-08-17

Introduzione

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

Domande pertinenti

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.

Letture associate

The Tokenization of Gold: A Financial Revolution Driven by Regulation

The Tokenization of Gold: A Regulation-Driven Financial Revolution In early 2025, anticipation of US tariffs triggered a rush to withdraw physical gold from the Bank of England, exposing the friction in London's $1.2 trillion gold market. While daily trading of $737 billion occurs via ownership certificates without moving bullion, demand for physical metal revealed a pricing split based on deliverability. This article explores why the UK's Financial Conduct Authority (FCA) is developing rules for tokenized gold, focusing regulation squarely on the ledger system. London's gold market, cleared by four major banks, performs four key functions: physical storage, quality verification, ownership registration, and credit provision. Tokenization excels at the third—offering cheap, precise ownership records—but fundamentally challenges the fourth by potentially rendering banks' credit intermediation obsolete. Currently, most gold is held in "unallocated" accounts, where investors are unsecured creditors of banks, trading speed for credit risk. Tokenized gold combines the instant transfer of unallocated accounts with the direct ownership claim of allocated bullion, eliminating bank risk. The FCA is prioritizing its use as collateral, where speed is critical, unlocking this vast pool of currently illiquid assets for margin calls. This shift is partly driven by post-2008 banking regulations like Basel III's Net Stable Funding Ratio, which penalized banks for holding unallocated gold. The push now comes from the清算 banks themselves, like HSBC, which have launched proprietary tokenization systems. The crucial regulatory decision will be whether these tokens are allowed to circulate outside their creators' closed ecosystems. True adoption will be visible in LBMA data: high overall trading volume paired with a decline in settlements through the traditional central ledger, as transactions move to instant blockchain transfers. Ultimately, tokenization doesn't replace the physical vaults, security, and assayers but could elevate their importance, shifting their revenue to standardized service fees. The revolution lies not in moving the gold, but in reinventing how its ownership is recorded and transferred.

marsbit10 min fa

The Tokenization of Gold: A Financial Revolution Driven by Regulation

marsbit10 min fa

Yield Leverage and Liquidity Leverage: The STONKBROKER Mechanism is Very Suitable for the RWA Scenario

The article argues that the STONKBROKER mechanism is highly suitable for Real-World Asset (RWA) tokenization scenarios due to its two key leverages: **Profit Leverage** and **Liquidity Leverage**. **Profit Leverage:** Traditional RWA models simply tie tokens to real-world asset yields. STONKBROKER's model is more engaging by allowing NFT holders to earn not only the underlying real-world cash flows but also additional yields generated from the on-chain system's own operations and transaction activity (like fees and slippage). This creates a dual income stream. **Liquidity Leverage:** Standard RWA asset bundles often suffer from poor liquidity. STONKBROKER's mechanism, which allows fixed-ratio swapping between NFTs and a platform's fungible token (and vice versa), solves this. It provides real-time market pricing and flexible exit options for each "RWA asset" NFT by unifying NFT liquidity with ERC-20 token liquidity via an AMM pool. This enhances capital efficiency and attracts more trading activity. The article further speculates on applying this model to broader RWAs (e.g., real estate, bonds). The core idea is to create a more dynamic, liquid, and profitable ecosystem where ordinary users can participate, combining real-world yields with the speculative and transactional energy of a crypto-native system. The author mentions being inspired by the launch of a project called @TheCardWall, which tokenizes high-grade physical trading cards.

marsbit30 min fa

Yield Leverage and Liquidity Leverage: The STONKBROKER Mechanism is Very Suitable for the RWA Scenario

marsbit30 min fa

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.

marsbit1 h fa

Deciphering TapeOut: A Child Built a CPU On-Chain

marsbit1 h fa

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.ru1 h fa

Novig Sues Wisconsin as Sports Prediction Market Dispute Heats Up

cryptonews.ru1 h fa

Trading

Spot
活动图片