惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

MyScale Blog
MyScale Blog
MongoDB | Blog
MongoDB | Blog
The Register - Security
The Register - Security
T
The Blog of Author Tim Ferriss
A
About on SuperTechFans
Vercel News
Vercel News
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Jina AI
Jina AI
Stack Overflow Blog
Stack Overflow Blog
Cisco Talos Blog
Cisco Talos Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
W
WeLiveSecurity
S
Securelist
I
Intezer
F
Full Disclosure
WordPress大学
WordPress大学
腾讯CDC
酷 壳 – CoolShell
酷 壳 – CoolShell
Latest news
Latest news
aimingoo的专栏
aimingoo的专栏
C
Cisco Blogs
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
T
The Exploit Database - CXSecurity.com
P
Proofpoint News Feed
K
Kaspersky official blog
阮一峰的网络日志
阮一峰的网络日志
P
Proofpoint News Feed
J
Java Code Geeks
人人都是产品经理
人人都是产品经理
雷峰网
雷峰网
AWS News Blog
AWS News Blog
T
Tenable Blog
Google DeepMind News
Google DeepMind News
B
Blog RSS Feed
L
LINUX DO - 最新话题
小众软件
小众软件
T
Threat Research - Cisco Blogs
C
Cyber Attacks, Cyber Crime and Cyber Security
The GitHub Blog
The GitHub Blog
爱范儿
爱范儿
N
News and Events Feed by Topic
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
量子位
H
Hackread – Cybersecurity News, Data Breaches, AI and More
Forbes - Security
Forbes - Security
cs.CV updates on arXiv.org
cs.CV updates on arXiv.org
U
Unit 42
O
OpenAI News
V
V2EX
T
Troy Hunt's Blog

Swift for Visual Studio Code comes to Open VSX Registry | InfoWorld

Notion courts developers with a platform for AI agents and workflow automation Using continuous purple teaming to protect fast-paced enterprise environments A better way to work with SQL Server Evidence-driven workflows: Rethinking enterprise process design AWS debuts Graviton-powered Redshift RG instances to cut analytics costs SAP’s AI promises last year? Most are still rolling out First look: Lemonade serves up local AI with limitations GitLab CEO sees developer tool bill increasing 100-fold Red Hat adds support for agentic AI development What’s new and exciting in JDK 26 Kill the loading spinner with local-first data and reactive SQL A networking revolution at AWS Tokenmaxxing is super dumb How to add AI to an existing product (without annoying users) Your AI doesn’t need another database What happens when engineering teams reorganize around AI agents Python isn’t always easy When cloud giants meddle in markets 12 model-level deep cuts to slash AI training costs The best new features in Python 3.15 Teradata launches platform for enterprise AI agents moving beyond pilots Three skills that matter when AI handles the coding MongoDB targets AI’s retrieval problem Building AI apps and agents with Microsoft Foundry Designing front-end systems for cloud failure No, AI won’t destroy software development jobs Diskless databases: What happens when storage isn’t the bottleneck Vibe coding or spec-driven development? The agentic AI distraction Vibe coding or spec-driven development? How to choose Cloud providers are blinded by agentic AI SAP to acquire data lakehouse vendor Dremio Small language models: Rethinking enterprise AI architecture Making AI work through eval hygiene Improving AI agents through better evaluations AI in the cloud is easy but expensive Running AI in the cloud is easy – and expensive Making AI work for databases Harness teams of agentic coders with Squad Harness teams of coding agents with Squad Oracle NetSuite announces AI coding skills for SuiteCloud developers Why it’s so hard to create stand-alone Python apps A new challenge for software product managers The hidden cost of front-end complexity GitHub shifts Copilot to usage-based billing, signaling a new cost model for enterprise AI tools OpenAI’s Symphony spec pushes coding agents from prompts to orchestration The front-end architecture trilemma: Reactivity vs. hypermedia vs. local-first apps Enterprise AI is missing the business core The best JavaScript certifications for getting hired Google begins putting the guardrails on agentic AI Why world models are AI’s next frontier Where to begin a cloud career Google pitches Agentic Data Cloud to help enterprises turn data into context for AI agents How open source ideals must expand for AI Is your Node.js project really secure? How I doubled my GPU efficiency without buying a single new card SpaceX secures option to acquire AI coding startup Cursor for $60B Google’s Gemma 4 shines on local systems – both big and small AI is upending the SaaS game How AI is upending SaaS tools Snowflake offers help to users and builders of AI agents From the engine room to the bridge: What the modern leadership shift means for architects like me Addressing the challenges of unstructured data governance for AI The cookbook for safe, powerful agents Enterprises are rethinking Kubernetes GitHub pauses new Copilot sign-ups as agentic AI strains infrastructure Best practices for building agentic systems Making agents dull Oracle delivers semantic search without LLMs When cloud giants neglect resilience Exciting Python features are on the way Ease into Azure Kubernetes Application Network The agent tier: Rethinking runtime architecture for context-driven enterprise workflows The two-pass compiler is back – this time, it’s fixing AI code generation MuleSoft Agent Fabric adds new ways to keep AI agents in line Salesforce launches Headless 360 to support agent‑first enterprise workflows Tap into the AI APIs of Google Chrome and Microsoft Edge Where will developer wisdom come from? GitHub adds Stacked PRs to speed complex code reviews The hyperscalers are pricing themselves out of AI workloads HTMX 4.0: Hypermedia finds a new gear Google Cloud introduces QueryData to help AI agents create reliable database queries Hands-on with the Google Agent Development Kit Are AI certifications worth the investment? AWS targets AI agent sprawl with new Bedrock Agent Registry Cloud degrees are moving online Swift for Visual Studio Code comes to Open VSX Registry AI agents aren't failing. The coordination layer is failing How Agile practices ensure quality in GenAI-assisted development Anthropic rolls out Claude Managed Agents Microsoft’s reauthentication snafu cuts off developers globally Meta’s Muse Spark: a smaller, faster AI model for broad app deployment Bringing databases and Kubernetes together Rethinking Angular forms: A state-first perspective Minimus Welcomes Yael Nardi as CBO to Facilitate Strategic Growth Microsoft announces end of support for ASP.NET Core 2.3 Get started with Python’s new frozendict type AWS turns its S3 storage service into a file system for AI agents Microsoft’s new Agent Governance Toolkit targets top OWASP risks for AI agents GitHub Copilot CLI adds Rubber Duck review agent
The winners and losers of AI coding
by Nick Hodges · 2026-04-08 · via Swift for Visual Studio Code comes to Open VSX Registry | InfoWorld

Goodbye and good riddance to all of those infuriatingly unmaintainable legacy balls of mud. Modern, bespoke replacements are on the horizon.

I don’t need to tell you that agentic coding is changing the world of software development. Things are happening so quickly that it’s hard to keep up. Internet years seem like eons compared to agentic coding years.  It seemed like just a few short weeks ago that everyone very suddenly stopped writing code and let Claude Code do all the work because, well, it was a few short weeks ago that it happened. 

It seems like new ideas, tools, and frameworks are popping up every day.

Despite things moving like a cheetah sprinting across the Savannah, I am going to make a few predictions about where the cheetah is going to end up and what will happen when it gets there. 

So long, legacy software

First, legacy software is going to become a thing of the past. You know what I’m talking about—those big balls of mud that have accreted over the last 30 years. The one started by your cousin’s friend who wrote that software for your dad’s laundromat and is now the software recommended by the Coin Laundry Association. The one with seven million lines of hopeless spaghetti code that no one person actually understands, that uses ancient, long-outdated technology, that is impossible to maintain but somehow still works. The one that depends on an entire team of developers and support people to keep running.

Well, someone is going to come along and write a completely fresh, new, unmuddy version of that ball of mud with a coding agent. The perfect example of this is happening in open source with Cloudflare’s EmDash project. Now don’t get me wrong. I have a deep respect for WordPress, the CMS that basically runs the internet. It’s venerable and battle-tested—and bloated and insecure and written in PHP.

EmDash is a “spiritual successor” to WordPress. Cloudflare basically asked, “What would WordPress look like if we started building it today?” Then they started building it using agentic coding, and basically did in a couple of months what WordPress took 24 years to do. Sure, they had WordPress as a template, but it was only because of agentic coding that they were even willing to attempt it. It’s long been thought foolish to say “Let’s rebuild the whole thing from scratch.” Now, with agentic coding, it seems foolish not to.

This is not the last creaky, old-school project that will be re-imagined in the coming days. If your business relies on a big ball of mud, it’s time to start looking at rebuilding it from the ground up before someone else beats you to it.

Ideas, implemented

Second, all those great application ideas you’ve been thinking about but could never find the time to do? Well, now you and millions of other developers can actually do them. I myself am nearing completion on six — six! — of the ideas I’ve been kicking around for years and never found the time to do. Yep, I build them all in parallel, with six different agents running at once. (Thank you, Garry Tan and gstack!)

Now, will there be a lot of slop that comes out of that? Sure. But will there be a huge supply of cool new software that will change the world? Yes, definitely. 

That project you’ve always wanted to do? You can do it now. 

Third, bespoke software will become the norm. Today, a business that needs accounting software will buy a product like Quickbooks or some other off-the-shelf solution, and adapt it to their way of doing things. But going forward, those businesses can create their own accounting package designed specifically for the way they do business. No one knows their domain better than the small business owner themselves. Instead of relying on someone who doesn’t understand the nuances of running your particular plumbing business, you can just talk to Claude Code and build your own solution. 

This is happening today (the head of finance wrote the solution!). If you aren’t considering becoming more efficient via agentic coding, then you might find yourself dealing with competitors that are.

Legacy apps need rewriting. Those side projects need building. That app you need for your business isn’t going to build itself. Three months ago, it all seemed foolish and impossible. Today? You are either the cheetah or the gazelle.