Atrophy CLI 工具发布：用 Elo 式评分对抗 vibe coding 技能退化

ai and ml

Want big muscles? Keep working out. Want big coding skillsets? Flex your dev skills with the Atrophy CLI app before they wither away

If you're a coder who uses AI agents to write programs for you, you may start losing those talents. Fortunately, a new command line tool can help reinforce your skills before they wither away.

Aptly titled Atrophy by Ashutosh Rath, the Bengaluru, India-based developer who created it, the CLI app treats coding abilities like Elo chess scores and pushes devs to reinforce their learning through regular drills in five different skill areas.

Syntax recall asks users to write a small function from a spec, debugging presents a code snippet with a hidden bug in it, code reading treats users like a human print command, API memory tests one’s ability to fill in the blank in a stdlib call, and decomposition tests a coder’s ability to outline a design.

Exercises test Python and JavaScript skills and come in three difficulty levels, Rath explained in the GitHub readme, with seeded generation for fresh variants of the different exercises.

“If AI assistance is quietly eroding your ability to code unaided, the chart shows you – before an interview, an outage, or a day without wifi does,” Rath wrote in Atrophy's readme.

Users take a baseline exam with one exercise in each of the five skill areas to get their starting ratings, which Rath estimates takes around 25 minutes to complete. After that, he recommends users do 5-10 minute drills two or three times a week. Atrophy automatically selects an exercise from the skill that’s been neglected the longest and sets a soft time limit for the exercise. Users can still pass if they exceed the soft limit, but point gain will be reduced if they do so.

Rath told The Register that ratings are adjusted after exercises “using an Elo-style formula,” and explained that drills early in one’s Atrophy use will move the number more than later ones. Inactivity in using the app (it has to be triggered manually right now and won’t force users to drill on any set schedule) weakens Atrophy’s confidence in the correctness of its user’s rating, but doesn’t actually lower scores.

Rath also suggests users take an AI-assisted drill once a month, scores for which are tracked separately and used to measure one’s skill gap between assisted and unassisted coding so you can see if you’re gradually becoming more dependent on agent assistance as time goes on.

As mentioned above, the rating system was based on chess Elo ratings, but Rath told The Register that it’s not a one-to-one copy of Elo’s ranking style. For one, each of the five skill areas is ranked independently and each starts at 1200. There isn’t a hard minimum or maximum, Rath explained, so just know you can keep dropping below 1200 if your coding muscles get really weak.

As Rath notes in the readme, drills are just a proxy for real-world skills, so don’t treat the number as an absolute measurement of skill: The value of Atrophy lies in the trends the app suggests over time, which allows devs to hone in on skill areas AI may be harming.

“Atrophy isn’t anti-AI,” Rath told us. “I built it to measure the gap between what I can do with AI and what I can still do on my own, because that skill can quietly rust without warning.”

MORE CONTEXT

Fixing Claude with Claude: Anthropic reports on AI site reliability engineering; This is your brain on bots: AI interaction may hurt students more than it helps; Some workers already let AI do the thinking for them, Microsoft researchers find; I vibe coded a feed reading web app. It was enlightening and uncomfortable

There’s plenty of evidence to suggest Rath is on to something. Analysts have been warning for some time that AI can erode skills due to reliance on tools to handle tasks traditionally left to human developers, but anecdotal evidence isn’t all the proof.

Researchers at MIT found last year that students writing essays with the assistance of AI chatbots had less brain activity than those writing them without LLM help. The cadre of users relying on AI also had poorer fact retention and an inability to recall what they had written. The end result of AI usage, they concluded, was “shallow encoding” of learning and less ability to operate independently of their agentic companions.

In other words, your skills could be disintegrating without you even realizing – might be time to take Atrophy for a spin so you can at least establish a baseline. ®

Fire up that iPhone 1 emulation and party like it's 2007

Browser-based fun to remember a time before Apple's annual cash grab became a thing

New motherboards, old RAM, plenty of life left in yesterday's PCs

DDR4 makes a comeback as component costs rise, while Linux offers an escape from forced upgrades

The VMware exit is a protection upgrade

PARTNER CONTENT: VergeIO says an exit is also an opportunity

Tiny11 puts Windows 11 on a diet without the PowerShell workout

New desktop app simplifies stripping out bundled software, with heavier cuts carrying security and support risks

It won't kill you, or humanity, to get off the AI upgrade treadmill

New models arrive so fast, we already have more new tech than it's possible to understand in a career

Cisco, Nvidia team up to build fatter, faster pluggable

If you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable

TOP STORIES

Anthropic asks users to stop being mean to Claude; '123456' password linked to Denmark data breach affecting 8.8M people; Microsoft and Anthropic play invoice tennis with startup's $17,600 Claude bill; Starlink's plan to avoid orbital near-misses: Ephemeris sharing; Shai-Hulud worm makes jump to AI infrastructure with Tensorlake compromise; Dutch tax office ditches Microsoft 365 cloud for on-premises alternative

Cisco, Nvidia team up to build fatter, faster pluggable If you thought 1.6 Tbps was fast, just wait, Cisco's USFP targets 12.8 Tbps in a single optical pluggable; Claude submitted fake murder tip to Philly police during summertime testing Anthropic took more than two months to alert cops; AI systems are fully capable of carrying out nightmare attacks against infrastructure and nobody's ready Meanwhile, AI agents move robotic arms, 'make OT device operator screens lie'; Nvidia found $1B under the couch to help secure American scientific computing dominance Commitment comes as GPUzilla prepares to fortify Uncle Sam's arsenal with at least seven AI-optimized supers; TSMC taps GlobalFoundries to bolster US silicon interposer production in $2B deal Advanced packaging tech is essential to the domestic production of high-performance semiconductors used in AI datacenters

Infosec

Security Russians are posing as Signal support to launch phishing attacks PLUS: US takes down Iranian propaganda sites; Marketing company asks 'Why Do We Have Your Information?' And more!; Security Microsoft patches failed to fix on-prem SharePoint, which is now under zero-day attack PLUS: China upgrades smartphone surveillance tools; Ring eases anti-snooping stance; and more; Black Hat and DEF CON DEF CON Franklin project enlists hackers to harden critical infrastructure Voting village reports have been so successful, says Jeff Moss, that the whole of DEF CON will now be included; Security EQT buys majority share in Swiss cybersecurity biz Acronis Went at equivalent of $3.5B+ valuation for entire firm, though portion sold not specified; Malware Month Ten years since the first corp ransomware, Mikko Hyppönen sees no end in sight On the plus side, infosec's a good bet for a long, stable career

FOSS

NetBSD may have found a new role: The AI-free FOSS OS Increasing awareness and adoption, followed by increasing donations; OpenAI dots inspire open source imitators amid technical difficulties Persistent agents appeal to AI companies, but demand isn't obvious; Ubuntu 'Stonking Stingray' beta swims out: Deeper Rust 'oxidization' plus LLM speech-to-text GNOME 51 is here, and Ubuntu interim releases are getting interesting again; Revive Raskin's 3 laws of software with humane work that considers a dev's duty of care All this, and angry NeoVim users; Firefox 157: Could bold new look be just what Mozilla needs?* Yet another new version of Firefox, with a significant reskin; KDE turns 30 and someone's brought an AI-native desktop proposal Akademy talk imagines Plasma assembling itself around a personal model of each user