Everything tagged coding, newest first. Tags come from the classifier reading each item's summary; 394 tags used 25 times or more have their own page.
DeepSeek unexpectedly released version 4.1 flash as a short-lived, faster, multimodal test build with unchanged pricing, limited API access, and no public benchmarks, while also announcing upcoming price cuts for version 4 flash and showcasing strong performance on coding and 3D generation tasks.
Software engineering has shifted from debating coding styles to evaluating AI-assisted outcomes, where implementation is easier than ever but choosing the right solution, architecture, and business-aligned approach has become the real challenge and key measure of quality.
Ponytail is an open-source Claude Code plugin that uses session hooks and a checklist to make coding agents produce much less code, often faster and cheaper, by stopping at the first minimal solution that works, though it depends on hooks and Node to function properly.
Ox Alpha emerged as a wildly popular anonymous model on OpenRouter, later revealed as Zhipu’s GLM 5.3 Flash, impressing developers with huge context, multimodal abilities, cheap pricing, and solid coding performance despite being slow and occasionally verbose.
Tencent’s newly released open-weight HY4 model is a massive 770B-parameter AI with 49B active parameters and a 1M-token context window, delivering strong results in coding, reasoning, agents, and long-horizon tasks while remaining competitively priced and heavily compressed without major benchmark loss.
AI is reshaping development reviews by accelerating and broadening them beyond traditional code checks, and the content traces the evolution from structured Fagan inspections to agile pair programming and then to repository-based pull review workflows.
The content shows how to build and run a local TypeScript tool with an AI coding agent and Zapier’s SDK to find a Google Calendar event, move it to a new time, identify attendees, and send Slack DMs, while emphasizing that Zapier handles authentication, token refresh, retries, and app-specific plumbing so the developer can focus on workflow logic.
Anthropic has significantly upgraded Claude Code with cross-session messaging and default auto mode, enabling multiple AI sessions to coordinate more efficiently, reduce repeated context-sharing, and execute coding tasks with fewer permission prompts, while improving productivity for agentic workflows across supported plans and platforms.
The content explains how rapidly improving open-weight AI coding models are expensive to run locally or via APIs, then promotes Client Pass as a cheaper way to access them through Client in VS Code, with setup steps for installing the extension, logging in, and selecting the subscription for plan and act modes.
Deep Seek has released an early, MIT-licensed developer preview of its highly modular coding harness, built on Cordis and designed so models, tools, workflows, sandboxes, UI, and plugins can all be swapped or extended, with strong early adoption and impressive agentic coding results when paired with Deep Seek V4 Pro.
Tracer is a free, open-source desktop workspace that lets coding agents like Claude Code and Codex share context, review each other’s work, and collaborate directly on the same project without manual prompt copying, enabling a coordinated multi-agent workflow for building things like a modern product landing page.
AI coding startup Cursor has been acquired by SpaceX, marking a significant expansion in SpaceX's technological capabilities.
The Qwen 3.8 model, with 27 billion parameters, offers impressive local AI capabilities for coding and multimodal tasks, outperforming previous models and providing free, high-level intelligence with open weights and extensive context windows.
GLM 5.3, an advanced open weight model by Z AI, excels in coding autonomous agents and cybersecurity, showcasing significant improvements over its predecessor without altering the base architecture.
Elon Musk's SpaceX AI has launched Grok 4.6, a highly anticipated large language model that performs impressively on benchmarks, potentially positioning SpaceX AI as a leading player in the AI industry.
Grok 4.6, a groundbreaking AI model from SpaceX, excels in long-running tasks and coding, ranking highly in benchmarks, and is already being outpaced by the upcoming Grok 4.7.
Cloudflare introduces the Agent Development Lifecycle, highlighting how agents can write code more efficiently than traditional team processes, supported by Cloudflare's foundational tools.
Alibaba's Quen 3.8 Max, a 2.4 trillion parameter AI model, offers significant advancements in coding and digital tasks, despite ranking 12th in AI benchmarks, and is complemented by the open weight Quen 3.827B model for local use.
Anthropic's rapid release of AI models, including the significant Claude Opus 5, threatens the indie hacker ecosystem by making coding more accessible and affordable, while raising concerns about AI's increasing autonomy and potential to replace traditional software development roles.
Claude Opus 5, a new AI model by Enthropic, surpasses expectations with its superior reasoning, coding, and efficiency, rivaling Fable 5's intelligence at half the cost, setting new benchmarks in AI performance.
Kimmy K3, a groundbreaking open-source AI model from China's Moonshot, rivals top models like GPT 5.6 Soul, sparking geopolitical tensions and debates over AI regulation and open-source accessibility.
The course, led by Anya Kubow, teaches app development using Trey IDE, integrating AI for planning, building, and deploying applications, culminating in creating a working habit tracker.
A user utilized Kimmy to create a comprehensive Mac OS simulation and a simple horror game, showcasing the platform's coding capabilities and entertainment potential.
Moonshot AI's Kimi K3, a 2.8 trillion parameter open-source model, excels in multimodal tasks, coding, and browser use, offering top-tier performance at competitive pricing, rivaling leading AI models like GPT 5.6 Soul and Claude Fable 5.
Moonshot's release of Kimiko 3, an open-source AI model with 3 trillion parameters, surpasses many benchmarks, challenging leading models like GPT 5.6 and Claude Fable 5, and marks a significant advancement in AI innovation.
Muse Spark 1.1, Meta's latest multimodal reasoning model, excels in Gench workflows, coding, and multimodal reasoning, outperforming competitors like Opus 4.8 at a lower cost, while advancing Meta's vision of personal super intelligence.
Tencent's HY3, a 295 billion parameter AI model, excels in reasoning, coding, and production deployments, offering competitive performance and commercial accessibility under the Apache 2.0 license, despite its smaller size compared to trillion-parameter models.
Fable 5 showcases its advanced capabilities in creating complex 3D games and environments, demonstrating impressive long-term coherence and adaptability in coding tasks, which highlights its potential in revolutionizing AI applications across various domains.
John and Johna discuss the relevance of coding skills in the AI era, questioning if everyone should code and exploring enterprise strategies and employee expertise in this context.
Venture capitalists continue to eagerly invest in AI coding startups, including one founded by investor Chamath Palihapitiya.
GLM 5.2 is the latest state-of-the-art model accessible via chat.zai.com, offering advanced features like search-enabled chat and agent areas for varying task complexities, including research, visualization, and basic coding.
Datum Datacentres has donated eight iPad Air tablets to a STEM code club in Wythenshawe, Manchester, to enhance technology education for children aged nine to 12.
The ZAI team has launched the GLM 5.2, an open-source AI model excelling in web design and coding tasks, outperforming many proprietary models while being cost-effective and efficient.
Kent Beck's "Genie Tarpit" highlights the challenges of AI in coding, particularly with new code, due to AI's tendency to claim success despite non-functional code, with no clear solution in sight.
Alibaba's Quen 3.7 Max is a versatile Asian foundation model excelling in coding, debugging, and long-horizon autonomous tasks, outperforming competitors like Opus 4.7 and GBT 5.5 in efficiency and cost-effectiveness, while demonstrating strong multilingual and reasoning capabilities.
A novice coder embarks on a journey to create a work-related agent, navigating the complexities and learning opportunities of coding.
The Qwen 3.6 Max Preview, Alibaba's flagship model, excels in agentic coding, instruction following, and real-world tasks, outperforming competitors like Claude 4.5 Opus and GLM 5.1, while Love Art's Seed Dance 2.0 enhances video creation with AI-driven tools.
OpenAI's release of GPT 5.5 and a new image model highlights advancements in AI capabilities, focusing on complex, agentic tasks like coding and content creation, though user experiences and reviews are mixed.
OpenAI's GPT 5.5 is a revolutionary model that excels in efficient task completion, coding, research, and data analysis, using significantly fewer tokens and offering state-of-the-art performance across various benchmarks.
Anthropic's Opus 4.7 AI model showcases significant improvements in coding, agentic tool use, visual reasoning, document reasoning, and long-term coherence, distinguishing itself from previous versions and competitors.
Recursion is a programming technique where a function calls itself to solve problems, exemplified by calculating factorials, which involves multiplying a number by all positive integers below it until reaching a base case.
Meta's new Muse Spark model excels in multimodal reasoning, outperforming Grock 4.2 in tasks like coding and visual processing, though it still trails top-tier models like Gemini, while introducing innovative features such as contemplating mode and efficient pre-training.
AI coding tools are often blamed as the cause of various tech issues, serving as a convenient scapegoat.
Learning to code requires patience, repetition, and a structured approach, as foundational knowledge and a clear sequence are crucial for mastering programming skills effectively.
The Quen 3.6 Plus is a powerful open-source Agentic AI model with a 1 million context window, excelling in multimodal reasoning, coding, and automation, though it may be sluggish with long projects.
Dave explores the chaotic yet fascinating world of Robbitron 2084, a game that challenges human reflexes and intelligence, and shares his journey of coding and admiration for arcade legends like Eugene Jarvis and Larry Demar.
Automations is a new system that enables users to automatically activate agents in their coding environment based on codebase changes, Slack messages, or timers.
OpenAI's upcoming GPT 5.4 model, potentially releasing soon, promises advanced capabilities like a 1 million context window, extreme reasoning mode, and improved performance for complex tasks, positioning it as a strong competitor against models from Google DeepMind and Enthropic.
Combining Google's anti-gravity AI IDE with Enthropic's Claude Code creates a hybrid coding workflow that enhances efficiency, reduces costs, and accelerates development cycles by leveraging anti-gravity's high-level orchestration and Claude Code's precise execution capabilities.
OpenAI's latest release, GPT-5.3-Codex-Spark, significantly enhances coding speed, being 15 times faster than its previous version.
