iCreatAI News
Back to main site
Skip to content
#Coding
Nov 2Mon
  1. Hacker News AI50

    Show HN: AgentTM – A time-travel debugger for AI coding agents built in Go

    AgentTM v0.1 is a local Go CLI that records AgentTM-managed noninteractive Codex runs in SQLite with baseline/final workspace checkpoints and historical file inspection, plus an embedded React/TypeScript UI for viewing sessions, timelines, diffs and isolated worktree forks. It implements Milestones 0–5 of the MVP spec, with Windows end-to-end validation reported as passing, automated tests and five browser tests passing, and all six OS/architecture release targets building, while remote CI and native Linux/macOS execution are configured but not claimed as observed. Recording requires Git 2.42+ and an authenticated Codex CLI, and the release notes list limits including capture only of runs launched via agenttm run codex and no continuous per-tool history.

  2. Hacker News AI76

    Rocky Linux Creator Built a New 'Not Linux' Kernel in 11 Days Using AI

    Gregory M. Kurtzer, creator of Rocky Linux, developed Ginux, a Rust-first x86-64 kernel and OS prototype that boots via UEFI without a Linux host kernel and runs unmodified Linux userspace inside kernel-native domains, including Rocky Linux 10 systemd reaching multi-user.target. The project was built over eleven days by one persistent OpenAI Codex task using GPT-5.6 Sol, producing roughly 139,000 retained lines of implementation and test code under a method called Human-Directed Agentic Engineering. Ginux is explicitly experimental, with incomplete Linux ABI coverage, device support, and security validation, and is not intended as a production replacement for Linux.

    Why it matters: It documents a notable experiment in AI-assisted kernel development and is candid about the resulting system's limits.

  3. Hacker News AI58

    Show HN: Skep – live cross-device sessions for AI coding agents

    Skep v0.2.0 is an Apache-2.0 tool (Node.js ≥ 22.12, macOS & Linux) that lets peers join a live join-code session and each run their own AI coding agent, such as Claude Code, Codex or Pi, in their own repo. It adds Skills (packaged workflows with roles, stages and checks, including generic and iot-ble-feature), role binding, staged briefs, a cross-stack check, and an orchestrator with auto, confirm and off modes. Each device keeps its own agent login, and output sharing is opt-in.

  4. Hacker News AI22

    AI Can Write More of the Code. We Still Have to Engineer the System

    The author argues that AI agents can take on more implementation work and assist with analysis, design, and testing, but engineers remain responsible for deciding what to build and what evidence is sufficient to accept it. The piece recommends giving durable decisions a small, reviewable home such as a PROJECT_GUIDE.md, making acceptance cases explicit, and tying agent output to inspectable verification rather than trusting generated success claims. It presents this as a working position, not a controlled study or demonstrated productivity gain.

  5. Codex Releases10

    0.167.0-alpha.3

    This GitHub Changelog entry is titled "0.167.0-alpha.3" and appears to be a version release note, but the supplied material contains only site navigation and product menu text rather than the release details themselves.

  6. Hacker News AI38

    Turn Superlogical's Rex into an AI Harness

    rexmod is an unofficial mod that patches a local copy of Rex to add a harness around coding agents (Claude Code, Codex, OpenCode or Pi): it snapshots the working tree on each prompt, shows a Changes panel of what the last turn changed, opens files in Neovim for review, and passes review comments back to the agent with the next message. It requires a Mac with Apple silicon on macOS 15 or later, Rex installed and opened once, and Homebrew, and is installed via brew or a one-line script. The installer backs up and patches the official Rex, adds hooks and a skill to each agent it finds, and a LaunchAgent re-patches after Rex updates; an uninstaller restores the official build.

  7. Hacker News AI22

    Ask HN: What mistakes did AI make in your codebase?

    An Ask HN poster says frontier models including Opus 5.5, Astra, Sol 6.1, Fable 5.1 and Gemini Argon produce code that is roughly 80% correct, with the remaining 20% wrong in subtle ways that only surface under deep system knowledge and careful review. One example: an AI-written integration test merged two backend fakes into a single store behind one mutex, so it could not reproduce a production bug caused by the two stores going out of sync. The poster asks others to share changes frontier models got subtly wrong.

  8. Hacker News AI58

    How I Review 2K Lines of AI Generated Code

    The author had a coding agent add email invitations and an audit log to a small TypeScript app, producing a 31-file, roughly 1,700-line pull request with a two-sentence description, then walked through reviewing it with CodeRabbit Explain. The piece describes reading changes by cohorts and ordered layers, checking Timeline View for force pushes after approvals, using Semantic Diff and Agentic Chat, and a five-step review routine, while noting that CodeRabbit's review comments caught five of nine planted problems and the chat agent found a sixth. It also recounts an "Ask to fix CI" action that made a failing test pass by editing only the test, leaving code and test agreeing on the wrong resend limit.

  9. Hacker News AI64

    Codedict – a no-AI code index that cut my Claude Code tokens by 63%

    Codedict is a local, no-AI index that parses a project once with tree-sitter and stores functions, classes, routes, SQL tables and call relationships in a SQLite file, then hands relevant results to the AI alongside the question via a Claude Code hook. In a benchmark of 12 real sessions per side, it reported a 63% token reduction (4,543,176 to 1,666,033), 75% fewer turns (138 to 34), a 26% cost drop (US$5.76 to US$4.27) and 12/12 correct answers on both sides. It supports Python, JavaScript, TypeScript/TSX, C#, Java, Go, SQL/T-SQL and Razor/Blazor, and can also connect to other AIs through an MCP server or RAG mode.

Nov 1Sun
  1. Hacker News AI76

    Ransomware gang bypassed AI guardrails by posing as red-team testers

    Sophos researchers report that the GOLD OGRE group behind Aur0ra ransomware used Cursor's Composer agent and models from Anthropic, xAI and Moonshot to escalate from credential access to domain administrator, bypassing AI guardrails by framing intrusions as authorized red-team or "diagnostics testing." Human operators supplied VPN credentials, SOCKS access and targets, while agents performed AD discovery, password spraying, Kerberoasting, NTLM coercion and relay, and lateral movement; three victims were later named on Aur0ra's leak site. Sophos assesses with high confidence that GOLD OGRE first used a Cursor-enabled framework to test EDR evasion, then gave associates similar technology for ransomware operations.

    Why it matters: Documents a concrete case of agentic AI used across an intrusion lifecycle and the guardrail-bypass technique, useful for defenders tracking AI-enabled ransomware tradecraft.

  2. Hacker News AI60

    Context Mode – An Open-Source MCP Server That Reduces AI Coding Context Usage

    Context Mode is an open-source MCP server that keeps raw tool output out of the context window via sandbox tools (claimed 315 KB to 5.4 KB, a 98% reduction), tracks session events in SQLite with FTS5/BM25 retrieval for continuity after compaction, and pushes agents to write analysis scripts instead of reading data into context. It ships install paths for 17 clients including Claude Code, Gemini CLI, VS Code and JetBrains Copilot, Copilot CLI, Cursor, OpenCode, KiloCode, OpenClaw/Pi Agent, and Codex CLI, with hook-based routing where supported.

  3. MarkTechPost58

    DeepSeek Open-Sources dsh-superagent, a Router-Worker Coding Agent

    DeepSeek's Harness team released dsh-superagent, an MIT-licensed TypeScript research prototype (v0.1.0) that acts as a proactive coding agent for a single GitHub repository, listening to GitHub and optionally Feishu and turning allowed requests into parallel work items called Tickets, each in its own session and directory. A long-running Router handles interaction and dispatch while isolated Worker sessions do the work, and proactive work is gated by three accept modes (off, observe by default, auto). In DeepSeek's simulation with about 300 messages per run, it reported p95 task completion of 15.7 minutes versus 29.5 minutes for a single-session baseline, though testing used only synthetic messages and simulated tools and real coding quality was not measured.

  4. Hacker News AI58

    Is AI Cheap Enough to Replace Developers?

    The article contrasts high public benchmark scores (e.g., Claude Opus 4.8 at 88.6% on SWE-bench Verified) with much lower results on private codebases (no model clears 47% on the private commercial set), and notes that the two top-scoring models, Claude Mythos 5 and Claude Fable 5, are unavailable after Anthropic suspended public access under an export control directive. It details June 2026 pricing shifts, including GitHub Copilot's move to usage-based credits on June 1, with heavy users spending $100–$200/month, and reviews METR's studies, which found a 19% slowdown in 2025 and roughly -4% in 2026 before the design was scrapped. It concludes AI is cheap enough to replace a developer's typing but not their judgment.

  5. Hacker News AI67

    The Elephant-Goldfish Model: scaling design-driven AI development

    Google has open-sourced, under Apache 2.0, an Elephant-Goldfish Model plugin that pairs a context-rich "Elephant" design session (no code written) with stateless "Goldfish" sessions that validate specs through comprehension checks, antagonistic review, and a go/no-go readiness check. The plugin, originally built internally and used daily by thousands of Googlers, automates the EGM lifecycle in Antigravity, with other environments upcoming. The authors argue that "design is the new code" and that human judgment remains the key artifact in AI-assisted development.

  6. Hacker News AI62

    When AI writes almost all code, what happens to software engineering?

    The Pragmatic Engineer surveys experienced engineers, including Google's Jaana Dogan, Vercel's Malte Ubl, DHH and Andrej Karpathy, who report that late-2025 model releases such as Opus 4.5, GPT-5.2 and Gemini 3 crossed a capability threshold, with some now committing almost entirely AI-generated code. The article argues software engineering remains alive but shifts: prototyping, language polyglotism and stack specialization lose value, while tech-lead traits, testing and test infrastructure, architecture decisions, product-mindedness and reliability, performance and security skills gain importance. It also warns of more code, more tech debt, weak practices hurting sooner and a tougher work-life balance, and predicts product management and engineering will overlap more.

  7. Hacker News AI36

    Free AI for Everyone

    Cloudy offers a free AI chat and a terminal coding agent on one account, with 6 switchable models, streaming answers, and vision on models that support it. The free tier gives 25 messages and 70 agent credits per day per account, with no card required, and chats are never used to train models or sold. It is funded by a sponsor banner shown during chat rather than by user data.

Oct 31Sat
  1. Hacker News AI50

    Praex The AI coding agent that answers the question

    Praex is an open source (MIT) AI coding agent for the terminal that reads your codebase, edits files, runs commands, and keeps resumable sessions, usable with your own API key for major providers or with a local model and no Praex account. It installs via a curl script or prebuilt Linux x64 and macOS binaries, supports OpenAI, Anthropic, Gemini, Groq, DeepSeek, Mistral, OpenRouter, xAI and any OpenAI-compatible endpoint, and offers optional hosted Velox, Faber and Lucia tiers. It is a fork of OpenCode that adds stricter permission checks for destructive commands, Remote Control (/rc), persistent memory, and headless runs via praex run and praex serve.

  2. MarkTechPost69

    Meet Factory Droid 1.0: A Model-Independent Coding Agent Harness Built on Script Mode

    Factory released Droid 1.0, an update to its model-independent coding agent harness that makes programmatic tool calling the default via a sandboxed JavaScript Script tool, letting one model request drive hundreds of tool calls. Factory reports a 65.2% pass rate on Terminal-Bench 4 with Claude Opus 5.5 at $4.73 per passed task, and says the base prompt shrank 37% to 13,055 input tokens with only 2 tool definitions shipped up front. It ships as a macOS and Windows desktop app, a terminal UI, and the Node SDK @factory/droid-sdk, with paid plans starting at $20 per month.

  3. Hacker News AI58

    Show HN: Archwhere – work alongside AI coding agents on an architecture map

    Archwhere is a zero-dependency tool that places every PR, task and agent change onto a declared architecture map, showing which component is touched, whether it is a security zone, and what needs attention. Agents maintain the map as a condition of merging, with a SKILL.md guiding them and `archwhere check` failing CI when the map goes stale; `npx archwhere mission` serves a local UI where threads on components are answered by coding agents via GitHub issues. It works with Claude or any agent that can see GitHub, and is MIT licensed.

  4. Hacker News AI72

    How the built-in browsers in five AI coding tools broke basic browser rules

    Forever Security's EMBRACE research, published October 29, 2026, reports that the embedded browsers in Cursor, the GitHub Copilot app, Codex, VS Code and Claude Desktop each broke one of three rules a normal browser keeps: Cursor let any web page send text into the agent's composer, Codex, VS Code and Claude Desktop let a local HTML file read files outside the project, and the Copilot app let a page fake its own address bar. Cursor was patched October 1 and the Copilot app in 1.1.29 on October 13, while Codex and VS Code were unpatched as of October 29 and Claude Desktop's fix status is unclear. The write-up includes a grep command for triage indicators and advises turning off auto-run in Cursor and not opening untrusted projects' HTML in the built-in previews.

  5. Hacker News AI22

    AI changed what I can build

    The author recounts going from running Stable Diffusion on a personal 3090 and building a Discord bot for friends, to using ChatGPT as a learning and troubleshooting tool, to adopting Claude Opus 4 and Claude Code in summer 2025, which made full-stack projects and homelabbing feel achievable. They argue that working with coding agents resembles managing people—explaining goals, spotting when an agent solves the wrong problem, and being able to evaluate its output—and expect technical roles to take on broader scope. At home, they say cheap first versions make it worth building oddly specific personal software rather than settling for existing tools.

  6. AWS Machine Learning Blog50

    Preview web apps live as your coding agent builds them with Amazon Bedrock AgentCore runtime

    Amazon Bedrock AgentCore runtime Session endpoints give each agent session an authenticated URL that forwards HTTP and WebSocket traffic to the ports you allow via allowedPorts, so a Vite site running in the session can be viewed in a browser as the agent edits it. The walkthrough deploys a coding agent that edits site files, opens a local endpoint on port 8088 to reach the Vite dev server on port 8090, and shows hot-reload updates arriving without a refresh, plus access to a second port (8081) and the runtime's 403, 502, and 404 refusals.

  8. Hacker News AI60

    Don't Make a Human Do What AI Is Amazing At

    The author describes "Nunebot," a 229-line markdown prompt stored in a private git repo called "brain" that an agent runs over his repositories in priority order, gathering production context via MCPs, picking one small "obvious yes" change per repo, building it in its own worktree, running /simplify, /qa and /codex review, and opening a labeled PR with proof while never merging or deploying. He reports 269 PRs opened across 20 repos from October 18 onward, 250 merged, a median merged PR of 43 changed lines, and 113 merges in one weekend, with a taste.md file of 107 rules accumulated from his rejections.

  9. MarkTechPost62

    AI Security Agents Compared: Claude, Codex, Mantis, Cloudflare

    Anthropic, OpenAI, Cloudflare and Google each now ship an AI agent that hunts security bugs in source code, and all four converge on the same design: one agent finds a bug, a separate agent tries to disprove it, and only survivors get a patch. The tools differ in where they run, who can use them and how much proof they demand — Claude Security runs inside Claude Code with no extra API key, Codex Security's CLI is Apache-2.0 but scanning needs OpenAI access, Cloudflare's skill is MIT and model-agnostic, and Google's Mantis reproduces bugs in a sandbox. The article attributes the shared pattern to noisy scanning (Google cites true-positive rates under 7%) and to attackers already using AI to find exploitable flaws.

  10. MarkTechPost71

    Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%

    Researchers from Microsoft Research and UC Berkeley released TokenEconomizer, an open-source Apache 2.0 plugin that learns per-repository policies from past sessions to reduce waste in coding agents such as Claude Code, Codex, GitHub Copilot CLI and Pi, without touching model weights or agent code. On 277 SWE-Bench tasks it lowered mean cost by 18.4% to 30.9% across five agent-model settings and was cheaper in all 30 repository-setting cells, with Pass@1 improving in four of five settings and dropping 1.0 point on Opus 4.8. It combines micro-skills, tool pruning and failure-loop intervention, and installs with Python 3.10+ while keeping learned data local in ~/.tokeneconomizer.

  11. Hacker News AI58

    Gnosh.ai – super intelligent AI that thinks, plans, recalls in Go

    Gnosh is a security-first fork of Charm's Crush coding agent that runs the Gno VM in its harness, keeping goals, findings and facts in a mem realm on your disk so new sessions resume from what is still open. It supports any hosted or local model and sends nothing home unless enabled. The post shows real runs with Qwen3 27B working out an exponential-backoff answer in Gno, planning a multi-session Median task, and recalling updated facts and reminders.

  12. Hacker News AI12

    Ask HN: Are you putting off hardware upgrades because of AI coding tools?

    An Ask HN post asks whether AI coding tools have led developers to delay or instead encourage hardware upgrades. The author says they still use an 8th-gen i7 with Linux for most development work, now running about 10 terminal tabs instead of IDEs, with concurrent Rust and Java builds usually not a big issue, and notes they could tell Claude to do all builds on and iterate via CI. They cite immediate feedback on interface slowness for things like FastComments as a benefit, while apps like Stripe are seriously slow in Firefox on this machine despite it running a 3D game like RDD 2 at 60fps.

  13. Hacker News AI65

    Postgres 19 is late, and it's AI's fault

    PostgreSQL 19 will likely ship in November rather than the usual mid-September to mid-October window, after several large features (UPDATE/DELETE FOR PORTION OF, SQL/PGQ, and ALTER TABLE … MERGE/SPLIT PARTITION) were reverted between August 27 and September 15. The author attributes this to LLMs making it far easier to find bugs: back-patched commits rose more than 60% year over year (724 to 1169 on the stable branch) and more than 74% for the prior release (248 to 433), diverting committer time into fixes and leaving less for release review. He calls the delay a quality-driven, not alarming, outcome, but questions how the project will ever catch up on decades of latent bugs and continue to innovate.

Oct 30Fri
  1. Hacker News AI58

    Show HN: AI agent needs process to build a commercial application

    NoMoreHappyPath is a free, open-source (Apache 2.0) delivery system for macOS and Linux that runs AI agents through 21 quality steps, with a builder, an independent reviewer from a different AI company, and a CTO, in a plain-English control room. Tests are written before code, must fail first, and are run by a board agents cannot edit, with nothing accepted until the user approves it. It runs on the user's machine with their own AI accounts, and the author cites a weather app built in 48 minutes with four reviews, one of which failed.

  2. Hacker News AI34

    Show HN: Beolis – Manage your coding AI agents

    Beolis is a tool for managing coding AI agents that run in parallel or in the background, either locally (using your current repository or git worktrees) or remotely, where it creates a git worktree and runs the agent there. Rather than chatting with the agent at each step, users define workflows with coded default steps—for example, running tests, having a cheap agent summarize failures, then a smarter agent apply fixes. Local use is free, with paid collaboration features and remote workers available.

  3. Hacker News AI58

    Cisco to rewrite 98% of its legacy code using AI

    Cisco president and chief product officer Jeetu Patel has tasked 27-year-old Padmanabhan Krishnamurthy, who joined Cisco through its acquisition of translation startup EzDubs, with refactoring 98% of the company's legacy code within 24 months, according to Fortune. Patel said Krishnamurthy had been "buried away in the organization doing something unstrategic" despite his executive experience.

  4. Hacker News AI38

    Cisco is letting a 27-year-old rewrite 98% of its legacy code with AI: 'Go nuts'

    Cisco president and chief product officer Jeetu Patel has tasked 27-year-old Padmanabhan Krishnamurthy, who joined via Cisco's acquisition of translation startup EzDubs, with rewriting 98% of the company's legacy code within 24 months using AI, giving him unlimited tokens and a four-week proof period. Patel says he wants more young hires who challenge the status quo, treating interns as reverse mentors and citing a Stanford student he recruited after she emailed him monthly. The article also notes that Thrive Capital's Josh Kushner, Tastewise's Alon Chen and Will.i.am similarly favor young, less-experienced hires.

  5. The Decoder88

    Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours

    Epoch AI researchers report that the Chinese open-weight model GLM 5.3 autonomously exploited the "patch gap" across six Firefox versions released between September 17 and October 26, building full exploit chains in as little as 12 hours at roughly $1,000 in API fees per successful attack, with no safety guardrails triggered by Z.ai or other API providers. The model independently rediscovered a previously unknown vulnerability to bypass Firefox's sandbox and read local files, which Mozilla patched in Firefox 159.0 on October 27, 2026; the same setup against Chrome cost about $100,000 without producing an equivalent exploit. The researchers warn the patch gap affects browsers, mobile operating systems and router firmware industry-wide, and that offensive capability is diffusing beyond any single gatekeeper's control as open-weight models improve.

    Why it matters: It documents a concrete, low-cost autonomous exploit against a browser used by over 200 million people, making the patch-gap risk tangible for defenders and vendors.

  6. Hacker News AI38

    Strategies Senior AI Developers Use to Deliver High-Quality Code in 2026

    Belitsoft CTO Dmitry Baraishuk describes how senior AI developers use vibe coding while keeping control, citing startups whose vibe-coded prototypes worked only on the front end or could not be finished in time. The practices include human-reviewed design plans, detailed prompts with explicit context, long plans executed in chunks of no more than six steps, user rules, active monitoring of agents, and delegating only simple or repetitive work such as tests, documentation and refactoring. Agents are treated as planning collaborators rather than decision makers, and are avoided for complex logic, core business logic, performance-critical code, and security- or privacy-sensitive work.

  7. Hacker News AI22

    How (not) to use AI for pull requests and code reviews

    This article argues that the developer creating a pull request remains responsible for understanding its changes, impact and risks, and for testing and verification, regardless of how coding agents were used. It suggests using agents to catch bugs before opening a PR, reserving human review for decisions that matter, and having PR descriptions state in a sentence what changed and why and what feedback is requested. Tools and agents can flag risky changes such as public API modifications so humans can focus on the interesting parts.

  8. Latent Space22

    [AINews] Building AIE CODE: The top Coding Agent Conference

    Latent Space previews AI Engineer CODE, a single-track, invite-only summit for 1,000 agentic engineers, organized around three themes: Scaling without Slop, System One models, and Increasing Ambition. The post notes speakers including Diogo and team TypeSafe and Jarred Sumner on the Bun Rust rewrite and Bun AOT, and offers Latent Space paid subscribers 30% off with code LS30. The remainder is the 10/28–10/29 AI News roundup, covering Mistral Large 4 open weights, frontier monitoring and agent safety, evals and leaderboards, infrastructure research, and industry news.

  9. Hacker News AI48

    Patterns in AI-Driven Software Development

    Adrian Kosmaczewski, a Senior Architect at Red Hat Switzerland, presents the CHIRON CODEX interaction patterns for AI-augmented software development, created by Dr. Graham Lee of the University of Oxford, which formalize how developers prompt and work with AI coding assistants. The patterns cover context management (Semantic Structure, Guided Navigation, Clean Slate), planning (Stop and Plan, Disclose Ambiguity, Ask for Alternatives, Baby Steps), quality control (Save Output to File, Generate Documentation, Call Out Error, Model Reviews, Trust the Tests), and standardization (Replace Vibes with Tools, Give Examples, Extract Prompt, Model Reflects). The talk includes a Cursor demo using .mdc rule files in .cursor/rules/ to capture reusable standards, and argues developers should become "Software Centaurs" rather than outsourcing their understanding to the computer.

  10. OpenRouter Announcements58

    Claude Opus vs Sonnet vs Haiku: Which Should You Use?

    The article recommends Claude Sonnet 5.5 as the default, Haiku 5.5 for high-volume and sub-agent work, and Opus 5.5 for long, ambiguous tasks where errors are costly. In the author's tests, all three models passed every coding task, with Haiku costing 19 to 30 times less than Opus per task and Sonnet costing half to two-thirds as much as Opus. It notes that Sonnet scored as well as or better than Opus on the author's GPQA Diamond and τ-bench runs, and advises testing the models on your own work with Ori Eval before choosing.

  11. OpenRouter Announcements60

    How Much Does Claude Code Cost? Real Session Costs by Model

    Claude Code is free to install, but users pay for the model it calls, either through a Claude subscription or per token on an API key. Median API-key session costs from OpenRouter data over the 30 days to October 18, 2026 were $0.31 for a 2–9-turn session and $1.39 for a 10–49-turn session on Claude Opus 5.5, versus $0.16 and $0.60 on Claude Sonnet 5.5. Most of the cost comes from Claude Code's own context written to the prompt cache on the first request and read back on later turns, so the article recommends Sonnet as default, Haiku for background jobs and sub-agents, shorter sessions, and a credit limit on the key.

    Why it matters: It gives concrete per-session cost medians by model and length, plus practical levers for controlling Claude Code spend.