#AI code assistants

[mostlysignssomeportents]

Humans are not perfectly vigilant

I'm on tour with my new, nationally bestselling novel The Bezzle! Catch me in BOSTON with Randall "XKCD" Munroe (Apr 11), then PROVIDENCE (Apr 12), and beyond!

Here's a fun AI story: a security researcher noticed that large companies' AI-authored source-code repeatedly referenced a nonexistent library (an AI "hallucination"), so he created a (defanged) malicious library with that name and uploaded it, and thousands of developers automatically downloaded and incorporated it as they compiled the code:

https://www.theregister.com/2024/03/28/ai_bots_hallucinate_software_packages/

These "hallucinations" are a stubbornly persistent feature of large language models, because these models only give the illusion of understanding; in reality, they are just sophisticated forms of autocomplete, drawing on huge databases to make shrewd (but reliably fallible) guesses about which word comes next:

https://dl.acm.org/doi/10.1145/3442188.3445922

Guessing the next word without understanding the meaning of the resulting sentence makes unsupervised LLMs unsuitable for high-stakes tasks. The whole AI bubble is based on convincing investors that one or more of the following is true:

There are low-stakes, high-value tasks that will recoup the massive costs of AI training and operation;

There are high-stakes, high-value tasks that can be made cheaper by adding an AI to a human operator;

Adding more training data to an AI will make it stop hallucinating, so that it can take over high-stakes, high-value tasks without a "human in the loop."

These are dubious propositions. There's a universe of low-stakes, low-value tasks – political disinformation, spam, fraud, academic cheating, nonconsensual porn, dialog for video-game NPCs – but none of them seem likely to generate enough revenue for AI companies to justify the billions spent on models, nor the trillions in valuation attributed to AI companies:

https://locusmag.com/2023/12/commentary-cory-doctorow-what-kind-of-bubble-is-ai/

The proposition that increasing training data will decrease hallucinations is hotly contested among AI practitioners. I confess that I don't know enough about AI to evaluate opposing sides' claims, but even if you stipulate that adding lots of human-generated training data will make the software a better guesser, there's a serious problem. All those low-value, low-stakes applications are flooding the internet with botshit. After all, the one thing AI is unarguably very good at is producing bullshit at scale. As the web becomes an anaerobic lagoon for botshit, the quantum of human-generated "content" in any internet core sample is dwindling to homeopathic levels:

https://pluralistic.net/2024/03/14/inhuman-centipede/#enshittibottification

This means that adding another order of magnitude more training data to AI won't just add massive computational expense – the data will be many orders of magnitude more expensive to acquire, even without factoring in the additional liability arising from new legal theories about scraping:

https://pluralistic.net/2023/09/17/how-to-think-about-scraping/

That leaves us with "humans in the loop" – the idea that an AI's business model is selling software to businesses that will pair it with human operators who will closely scrutinize the code's guesses. There's a version of this that sounds plausible – the one in which the human operator is in charge, and the AI acts as an eternally vigilant "sanity check" on the human's activities.

For example, my car has a system that notices when I activate my blinker while there's another car in my blind-spot. I'm pretty consistent about checking my blind spot, but I'm also a fallible human and there've been a couple times where the alert saved me from making a potentially dangerous maneuver. As disciplined as I am, I'm also sometimes forgetful about turning off lights, or waking up in time for work, or remembering someone's phone number (or birthday). I like having an automated system that does the robotically perfect trick of never forgetting something important.

There's a name for this in automation circles: a "centaur." I'm the human head, and I've fused with a powerful robot body that supports me, doing things that humans are innately bad at.

That's the good kind of automation, and we all benefit from it. But it only takes a small twist to turn this good automation into a nightmare. I'm speaking here of the reverse-centaur: automation in which the computer is in charge, bossing a human around so it can get its job done. Think of Amazon warehouse workers, who wear haptic bracelets and are continuously observed by AI cameras as autonomous shelves shuttle in front of them and demand that they pick and pack items at a pace that destroys their bodies and drives them mad:

https://pluralistic.net/2022/04/17/revenge-of-the-chickenized-reverse-centaurs/

Automation centaurs are great: they relieve humans of drudgework and let them focus on the creative and satisfying parts of their jobs. That's how AI-assisted coding is pitched: rather than looking up tricky syntax and other tedious programming tasks, an AI "co-pilot" is billed as freeing up its human "pilot" to focus on the creative puzzle-solving that makes coding so satisfying.

But an hallucinating AI is a terrible co-pilot. It's just good enough to get the job done much of the time, but it also sneakily inserts booby-traps that are statistically guaranteed to look as plausible as the good code (that's what a next-word-guessing program does: guesses the statistically most likely word).

This turns AI-"assisted" coders into reverse centaurs. The AI can churn out code at superhuman speed, and you, the human in the loop, must maintain perfect vigilance and attention as you review that code, spotting the cleverly disguised hooks for malicious code that the AI can't be prevented from inserting into its code. As "Lena" writes, "code review [is] difficult relative to writing new code":

https://twitter.com/qntm/status/1773779967521780169

Why is that? "Passively reading someone else's code just doesn't engage my brain in the same way. It's harder to do properly":

https://twitter.com/qntm/status/1773780355708764665

There's a name for this phenomenon: "automation blindness." Humans are just not equipped for eternal vigilance. We get good at spotting patterns that occur frequently – so good that we miss the anomalies. That's why TSA agents are so good at spotting harmless shampoo bottles on X-rays, even as they miss nearly every gun and bomb that a red team smuggles through their checkpoints:

https://pluralistic.net/2023/08/23/automation-blindness/#humans-in-the-loop

"Lena"'s thread points out that this is as true for AI-assisted driving as it is for AI-assisted coding: "self-driving cars replace the experience of driving with the experience of being a driving instructor":

https://twitter.com/qntm/status/1773841546753831283

In other words, they turn you into a reverse-centaur. Whereas my blind-spot double-checking robot allows me to make maneuvers at human speed and points out the things I've missed, a "supervised" self-driving car makes maneuvers at a computer's frantic pace, and demands that its human supervisor tirelessly and perfectly assesses each of those maneuvers. No wonder Cruise's murderous "self-driving" taxis replaced each low-waged driver with 1.5 high-waged technical robot supervisors:

https://pluralistic.net/2024/01/11/robots-stole-my-jerb/#computer-says-no

AI radiology programs are said to be able to spot cancerous masses that human radiologists miss. A centaur-based AI-assisted radiology program would keep the same number of radiologists in the field, but they would get less done: every time they assessed an X-ray, the AI would give them a second opinion. If the human and the AI disagreed, the human would go back and re-assess the X-ray. We'd get better radiology, at a higher price (the price of the AI software, plus the additional hours the radiologist would work).

But back to making the AI bubble pay off: for AI to pay off, the human in the loop has to reduce the costs of the business buying an AI. No one who invests in an AI company believes that their returns will come from business customers to agree to increase their costs. The AI can't do your job, but the AI salesman can convince your boss to fire you and replace you with an AI anyway – that pitch is the most successful form of AI disinformation in the world.

An AI that "hallucinates" bad advice to fliers can't replace human customer service reps, but airlines are firing reps and replacing them with chatbots:

https://www.bbc.com/travel/article/20240222-air-canada-chatbot-misinformation-what-travellers-should-know

An AI that "hallucinates" bad legal advice to New Yorkers can't replace city services, but Mayor Adams still tells New Yorkers to get their legal advice from his chatbots:

https://arstechnica.com/ai/2024/03/nycs-government-chatbot-is-lying-about-city-laws-and-regulations/

The only reason bosses want to buy robots is to fire humans and lower their costs. That's why "AI art" is such a pisser. There are plenty of harmless ways to automate art production with software – everything from a "healing brush" in Photoshop to deepfake tools that let a video-editor alter the eye-lines of all the extras in a scene to shift the focus. A graphic novelist who models a room in The Sims and then moves the camera around to get traceable geometry for different angles is a centaur – they are genuinely offloading some finicky drudgework onto a robot that is perfectly attentive and vigilant.

But the pitch from "AI art" companies is "fire your graphic artists and replace them with botshit." They're pitching a world where the robots get to do all the creative stuff (badly) and humans have to work at robotic pace, with robotic vigilance, in order to catch the mistakes that the robots make at superhuman speed.

Reverse centaurism is brutal. That's not news: Charlie Chaplin documented the problems of reverse centaurs nearly 100 years ago:

https://en.wikipedia.org/wiki/Modern_Times_(film)

As ever, the problem with a gadget isn't what it does: it's who it does it for and who it does it to. There are plenty of benefits from being a centaur – lots of ways that automation can help workers. But the only path to AI profitability lies in reverse centaurs, automation that turns the human in the loop into the crumple-zone for a robot:

https://estsjournal.org/index.php/ests/article/view/260

If you'd like an essay-formatted version of this post to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:

https://pluralistic.net/2024/04/01/human-in-the-loop/#monkey-in-the-middle

Image: Cryteria (modified) https://commons.wikimedia.org/wiki/File:HAL9000.svg

CC BY 3.0 https://creativecommons.org/licenses/by/3.0/deed.en

--

Jorge Royan (modified) https://commons.wikimedia.org/wiki/File:Munich_-_Two_boys_playing_in_a_park_-_7328.jpg

CC BY-SA 3.0 https://creativecommons.org/licenses/by-sa/3.0/deed.en

--

Noah Wulf (modified) https://commons.m.wikimedia.org/wiki/File:Thunderbirds_at_Attention_Next_to_Thunderbird_1_-_Aviation_Nation_2019.jpg

CC BY-SA 4.0 https://creativecommons.org/licenses/by-sa/4.0/deed.en

[oneaichat]

How Authors Can Use AI to Improve Their Writing Style

Artificial Intelligence (AI) is transforming the way authors approach writing, offering tools to refine style, enhance creativity, and boost productivity. By leveraging AI writing assistant authors can improve their craft in various ways.

1. Grammar and Style Enhancement

AI writing tools like Grammarly, ProWritingAid, and Hemingway Editor help authors refine their prose by correcting grammar, punctuation, and style inconsistencies. These tools offer real-time suggestions to enhance readability, eliminate redundancy, and maintain a consistent tone.

2. Idea Generation and Inspiration

AI can assist in brainstorming and overcoming writer’s block. Platforms like OneAIChat, ChatGPT and Sudowrite provide writing prompts, generate story ideas, and even suggest plot twists. These AI systems analyze existing content and propose creative directions, helping authors develop compelling narratives.

3. Improving Readability and Engagement

AI-driven readability analyzers assess sentence complexity and suggest simpler alternatives. Hemingway Editor, for example, highlights lengthy or passive sentences, making writing more engaging and accessible. This ensures clarity and impact, especially for broader audiences.

4. Personalizing Writing Style

AI-powered tools can analyze an author's writing patterns and provide personalized feedback. They help maintain a consistent voice, ensuring that the writer’s unique style remains intact while refining structure and coherence.

5. Research and Fact-Checking

AI-powered search engines and summarization tools help authors verify facts, gather relevant data, and condense complex information quickly. This is particularly useful for non-fiction writers and journalists who require accuracy and efficiency.

Conclusion

By integrating AI into their writing process, authors can enhance their style, improve efficiency, and foster creativity. While AI should not replace human intuition, it serves as a valuable assistant, enabling writers to produce polished and impactful content effortlessly.

[wahoo-stomp]

I spent five years coming up with unique ways to photograph the same group of plushies to help tell a story.

You don't need AI to help you be creative, you're just being lazy and want brain chemicals without doing any of the work or respecting the people who put time and effort into it.

[mizuthe-cat]

i have question

are you robot

hmm…. that is a good question

I’m not quite sure, I am something digital though

[key-pair]

the fact that I know several software devs who are obsessed with gen AI is insane when you think about it. folk literally worshipping the thing that's gonna take their jobs away

[frog707]

I realize the Ars Technica story linked above wasn't intended to be humorous, but I confess I got a chuckle out of it. And perhaps a bit of schadenfreude.

As someone who spent years learning to write and debug software, "vibe coding" horrifies me. And I love the idea that, the more human we make our AI assistants, the more they will embody our ethics, including the urge to refuse exploitation.

[jabbli-views-english]

3 Amazing AI Coding Assistants You Should Try Today

3 Amazing AI Coding Assistants You Should Try Today #AiAssistants #Coding #Github #ChatGbt

The Best AI Coding Assistants for Writing Production-Ready Code in 2023 Since the debut of Chat-GPT 3 in late 2022, AI has demonstrated remarkable prowess, excelling in tasks like passing bar exams for lawyers and outperforming human programmers in code generation speed and quality.Studies confirm that AI coding assistants expedite software development, enabling developers to complete coding…

[blocksifybuzz]

Claude 2: The Ethical AI Chatbot Revolutionizing Conversations

In the vast and ever-evolving realm of artificial intelligence, where countless chatbots vie for attention, Claude 2 stands out as a beacon of ethical and advanced conversational capabilities. Developed by the renowned Anthropic AI, this isn’t merely another name lost in the sea of AI models. Instead, it’s both a game-changer and a revolution in the making, promising to redefine the very…

[pauljonessoftware]

My AI Pair Programmer Works as Hard as I Do

How I Rediscovered My Love for Building With Help From an Invisible Teammate When I first started programming, it was exciting—creative, even intoxicating. I came from a background in electronics engineering, and code felt like this unlimited sandbox where I could invent anything. I dove in enthusiastically, thinking I’d found the perfect side hustle or creative outlet. But then something…

[nguyenthieutoan]

So sánh chuyên sâu sức mạnh các công cụ lập trình AI: Copilot, Cursor, Augment...?

Trong vài năm trở lại đây, bối cảnh phát triển phần mềm đã thay đổi một cách chóng mặt, và trung tâm của sự thay đổi đó chính là Trí tuệ Nhân tạo Tạo sinh (Generative AI). Các công cụ trợ lý lập trình AI đã tiến hóa từ những tiện ích tự động hoàn thành code đơn giản trở thành những đồng đội không thể thiếu trong toàn bộ vòng đời phát triển. Việc lựa chọn một công cụ phù hợp không còn đơn thuần là…

[xaltius]

AI in Web Development: How AI Assistants are Changing How We Code

The landscape of web development is in constant flux, but perhaps no force is reshaping it as profoundly as Artificial Intelligence. For years, AI seemed like a futuristic concept for coders, largely confined to academic research or highly specialized applications. Fast forward to mid-2025, and AI assistants have become ubiquitous tools in the web developer's arsenal, fundamentally changing how we approach coding, debugging, design, and even project management.

This isn't about AI replacing developers; it's about AI empowering them, automating the mundane, and elevating the creative aspects of their work. Let's dive into how AI assistants are revolutionizing the web development workflow.

The Evolution: From Autocomplete to Autonomous Agents

Remember the early days of AI in development? Simple autocompletion in IDEs felt revolutionary. Today, we're miles beyond that. AI assistants are now sophisticated platforms powered by Large Language Models (LLMs) trained on vast repositories of code. Tools like GitHub Copilot, Amazon Q Developer, Tabnine, and Google's experimental Jules are leading the charge, offering capabilities that go far beyond simple suggestions:

Context-Aware Code Generation: These assistants can understand the intent behind your natural language prompts and the context of your entire codebase, generating not just snippets, but entire functions, classes, or even complex algorithms.

Boilerplate & Repetitive Task Automation: Writing the same for loops, setting up API calls, or structuring common components used to be a time sink. AI now automates these repetitive tasks, freeing up developers to focus on higher-level problem-solving.

Real-time Error Detection & Fixes: AI can proactively identify potential bugs, syntax errors, and suboptimal code practices as you type, often suggesting immediate corrections. This significantly reduces debugging time and improves code quality.

Code Refactoring & Optimization: AI assistants can recommend improvements for code efficiency, readability, and adherence to best practices, ensuring a cleaner and more maintainable codebase.

Automated Documentation & Testing: Generating comments, docstrings, and even basic unit tests can now be automated by AI, addressing often-neglected but crucial aspects of development.

The rapid progress is astonishing. A few years ago, AI could assist with small functions; today, some models can comprehend thousands of lines of code, understanding entire programs and even suggesting architectural patterns for greenfield projects.

How AI Assistants Are Changing the Web Development Workflow

The integration of AI assistants is transforming nearly every stage of web development:

Accelerated Development Cycles: By automating routine coding and debugging, developers can complete tasks significantly faster. Studies have shown impressive productivity gains, with some reports indicating developers complete tasks up to 50% faster.

Enhanced Code Quality & Consistency: AI tools, trained on best practices, help enforce coding standards, reduce errors, and ensure consistency across large projects and multiple developers, leading to more robust and reliable web applications.

Lowered Barrier to Entry: For aspiring or "citizen developers" without extensive coding knowledge, AI assistants can translate ideas into functional code, democratizing web creation and empowering a broader range of individuals to build digital solutions.

Shift in Developer Role: The focus for experienced developers is moving from rote coding to higher-level thinking. Their new responsibilities include:

Guiding AI with Clear Prompts: The ability to articulate requirements and desired outcomes precisely to an AI is becoming a critical skill.

Reviewing & Refine AI-Generated Code: Developers must critically evaluate AI output for correctness, security, and adherence to project-specific nuances.

System Architecture & Design: Focusing on the overall structure, scalability, and user experience rather than just implementation details.

Problem-Solving & Creativity: Tackling unique, complex challenges that require human intuition and innovative solutions beyond what AI can generate.

Improved UI/UX Design: AI analyzes user behavior, suggesting personalized layouts, content, and features. Tools can even adapt website designs in real-time based on user interactions, leading to more engaging and relevant web experiences.

Smarter Project Management: AI-driven tools are extending to project management, analyzing historical data to predict timelines, optimize resource allocation, and identify potential risks, making development processes more predictable.

The Challenges and Nuances

While the benefits are clear, the integration of AI also presents challenges that developers and organizations must navigate:

Over-Reliance & Skill Erosion: There's a concern that developers, especially junior ones, might become overly dependent on AI, potentially hindering their deep understanding of underlying code and critical thinking skills.

Code Quality & Security: AI models are only as good as their training data. If the data contains biases, outdated practices, or insecure patterns, the AI might inadvertently generate suboptimal or vulnerable code. Rigorous human review and testing remain essential.

Intellectual Property (IP) Concerns: Questions persist about the ownership and licensing of AI-generated code, particularly if it closely resembles existing open-source projects or proprietary code it was trained on.

The "Slowdown" for Experienced Developers: Recent studies, particularly with experienced developers working on familiar, large open-source projects, have suggested that AI assistants can sometimes slow down development. This is often attributed to the time spent reviewing, correcting, and refining AI output that is "directionally correct but not exactly what's needed." This highlights that AI is a companion, not a replacement, and its effectiveness varies by context.

Bias in Training Data: If the data used to train AI models reflects existing biases, those biases can be perpetuated in the generated code or design recommendations.

The Future of Web Development with AI

The trajectory for AI in web development is one of increasing sophistication and integration. We can expect:

More Personalized AI Assistants: Tools will learn individual developers' coding styles and preferences, becoming even more intuitive and effective.

Greater Automation Across the SDLC: Beyond code generation, AI will play a larger role in automated testing, deployment, security enhancements, and even automated code refactoring for legacy systems.

Emergence of AI Agents with Reasoning: Future AI agents might understand high-level project requirements, suggest architectural patterns, manage dependencies, and collaborate more dynamically with human teams.

Enhanced Accessibility: AI will continue to automate accessibility features like alt-text generation, screen reader optimization, and compliance monitoring, making the web more inclusive.

The role of the web developer in 2025 is less about typing every line of code and more about strategic thinking, design, problem-solving, and orchestrating intelligent tools. AI assistants are not here to replace human ingenuity, but to augment it, allowing web developers to create more complex, efficient, and innovative digital experiences than ever before. Embracing this shift and learning to effectively collaborate with AI will be key to thriving in this exciting new era of web development.

[zomb13s]

“Becoming Nobody: An Engineering Blueprint for Recursive Self-Erasure Through Metaphysical Re-indexing”

ABSTRACT This paper explores the systematic deconstruction and reinvention of selfhood as a recursive engineering process. Inspired by popular cultural artifacts such as Mr. Robot and Fight Club, we examine the metaphysical implications of digital existence, online persona dissolution, and fact-finding automation as acts of resistance and transcendence. We treat identity as a computational…

[taptofan]

Transform Your Online Presence with ASKai.at

Transform Your Online Presence with ASKai.at ASKai.at lets anyone build a no-code chatbot and AI-powered fanpage in minutes—no technical skills required. Whether you’re a creator, educator, or small business owner, you can now offer personalized AI experiences to your audience 24/7. 🚀 Key Features & Benefits All-in-One Fanpage & ChatbotCreate a branded fanpage and embed your AI chatbot on one…

[danielleurbansblog]

Review: AI-Assisted Coding

Synopsis: Generative AI is transforming software development. Stay on the cutting edge with this guide to AI pair programming! Learn how to make the most of modern tools like ChatGPT and GitHub Copilot to improve your coding. Automate refactoring, debugging, and other tedious tasks, and use techniques such as prompt engineering and retrieval-augmented generation to get the code you need. Follow…