GoKawiil
Tech News
Developer Ayghri released i-have-adhd, an open-source skill/plugin for coding assistants like Claude Code that rewrites how the AI communicates: it leads with the next action, numbers steps, gives time estimates, caps lists, and cuts preambles, tangents and closing pleasantries. It installs via a CLI prompt pointing to the project's GitHub repo and can be customized by forking and editing its SKILL.md rules file.
A researcher evaluated 26 different prompt conditions—ranging from 'use TDD' to formal methods like Lean 4, TLA+, and SMT solvers—to see whether simply instructing coding agents to apply specific testing techniques or libraries improves the correctness of Rust implementations of Zstd. Four popular testing 'skills,' including ones with hundreds of thousands of GitHub stars, were also tested alongside a self-written skill, using the same Zstd benchmark from prior agentic programming comparisons.
A software developer recounts that their business partner used an AI coding assistant to build an entire payments backend module in a single day, then submitted a 5,236-line pull request without testing it. The developer found the endpoints didn't actually work and that documentation was riddled with obvious AI-generated filler, while missing critical details like where to obtain API keys.
Google's 2025 DORA report finds 90% of developers now use AI daily, but the tool mainly magnifies existing habits rather than automatically improving output quality. Separate data shows 66% of developers spend extra time fixing AI-generated code that's 'almost correct,' while GitClear found an eightfold rise in code duplication since AI adoption became widespread. The piece argues that cheaper development means weak feature ideas can ship as fast as good ones unless teams deliberately slow down to validate problems first.
xAI's Grok Build is a terminal-based AI coding assistant that supports mouse clicks for navigation but requires an external editor like Visual Studio Code for direct code edits, unlike rivals such as Google's Antigravity that bundle a full IDE. Users can prompt it to explain a codebase, install dependencies, run a web app, or build one from scratch and get deployment guidance, then iterate with further prompts. Access depends on a Grok plan, with free users hitting token limits quickly and paid SuperGrok tiers ($30 to $300 monthly) offering higher weekly caps.
Vibe coding, the practice of using AI language models to write software with minimal manual coding, is drawing scrutiny after Georgia Tech researchers linked dozens of security vulnerabilities directly to AI-generated code in just a three-month sample. Despite these risks, a survey of over 1,100 professional programmers found that 72 percent use AI coding tools daily, with AI-generated or -assisted code making up 42 percent of their codebases and expected to exceed half by next year.
A software engineering essay, part of a series called 'Conquering Entropy,' examines how AI-generated code changes the trust relationships within engineering organizations—from trusting the ticket author and reviewing engineer to trusting test suites, CI/CD pipelines, and even AI-driven site reliability tools. The author argues that as AI agents make code generation faster and cheaper, teams need explicit accountability: whoever ships a PR should be responsible for fixing it if it breaks in production.
A growing number of individual investors are using generative AI to write custom trading scripts and delegate portfolio decisions to automated agents, effectively mimicking strategies once reserved for professional quant funds. This trend, sometimes called 'vibe-coding,' lets non-programmers describe a trading idea in plain language and have AI translate it into executable code.
An Entrepreneur contributor argues that while AI coding agents have been rapidly embraced by software teams, autonomous agents for go-to-market functions like sales and marketing remain underused. The piece attributes this gap not to AI capability limits but to fragmented, duplicated sales data that lacks connection to reliable external signals needed for commercial decisions.
A robotics developer describes attempting to offload the tedious process of visually debugging robot code to an LLM coding assistant equipped with an image encoder and MCP server access to a visualizer tool. The experiment largely failed: the assistant lacked an intuitive sense of what correct robot behavior looks like and struggled to navigate the debugging GUI, taking minutes to reach a viewpoint the developer could reach in seconds.
Google is reportedly preparing to launch Gemini 3.8 Flash imminently, a model DeepMind's internal testing found outperforms Anthropic's Opus on coding tasks. The release would follow Gemini 3.7 Flash, launched just weeks earlier, and comes as Google shelves plans for a separate Gemini 3.5 Pro model, pushing the next Pro-tier release to Gemini 4.0.
Creator Peter Steinberger and his team released OpenClaw 2.0, a major overhaul of the open-source AI agent harness that lets users direct autonomous AI workers through messaging apps. The update, officially v2026.8.1, adds a rebuilt browser workspace, shared cloud sessions for multiple users, and expanded security features like sandboxing, role-based permissions and audit controls. Steinberger said the team built the new version largely by using OpenClaw itself to develop it.