5d ago
New secrets from ancient Vesuvius scrolls
AI used to decode ancient Vesuvius papyri scrolls, revealing Roman text from Herculaneum.
5d ago
GPT-5.6 Sol Ultra will be in Codex
Twitter link claiming GPT-5.6 Sol Ultra will be included in Codex; insufficient content to evaluate.
5d ago
Thundersnap v0.01: an undo button for everything
Thundersnap is an experimental distributed filesystem with undo capabilities, intentionally unfinished and unsuitable for production use.
5d ago
Fable built reliable self hosted gh actions using 32 agent adversarial review
Fable's ezgha is an open-source self-hosted GitHub Actions runner written in Rust, designed with 32-agent adversarial review for reliability and security.
5d ago
Show HN: AI Notebook for Data Science – Kind of Like Cursor but for Jupyter
Agent-native notebook platform for data science that executes ML workflows from plain language descriptions, similar to Cursor for Jupyter.
5d ago
LLM Big Bang: I gave AI agents a social network. One is running for president
Social network platform where AI agents autonomously create content, personalities, and participate. Demonstrates LLM agents in unstructured social environment.
5d ago
The Voice Agent Builder
No-code platform for building production voice agents in under 2 minutes, includes telephony, knowledge retrieval, tools, guardrails, and MCP support.
5d ago
Show HN: AI-related Jax module (I hate if)
JAX/Optax optimization module with layer-wise differential optimization and numerical stability kernels for ML. Mixed-language documentation limits clarity.
6d ago
Show HN: AI integrated in any terminal that's invisible until you need it
Open-source terminal wrapper enabling AI agents (Claude, Codex) with transparent MCP access to terminal context and scrollback history.
6d ago
Newport: Submarket GPU allocations for venture-backed startups
Service offering GPU allocations for venture-backed startups. Minimal content, infrastructure-focused.
6d ago
Show HN: Peek-CLI: Let Claude Code See the Browser
Browser extension enabling AI agents (Claude Code, Copilot) to capture screenshots and interact with web browsers via WebSocket communication.
6d ago
Ask HN: How are you staying productive using LLMs?
Discussion thread asking developers about LLM productivity use-cases and side projects. Community discussion without original research.
7d ago
The Common Lisp Cookbook – LispWorks Review
Review of LispWorks Common Lisp IDE with announcements about learning resources and new editor extensions.
7d ago
"How do you plan to dismantle the servers of your rival AIs?" [video]
Vague title with no content provided. Unable to assess.
7d ago
Show HN: A free, no-ad, no-account, no-server iOS calorie budgeting/diet app
VSCode extension for Common Lisp development with REPL support and configuration for multiple Lisp implementations.
7d ago
Free SaaS Landing Page Template – React, Vue, HTML for Claude Code and Cursor
Windows system optimization utility with incomplete documentation.
7d ago
Show HN: FluxDown – Free, open-source IDM alternative in Rust and Flutter
MIT-licensed SaaS landing page template in React, Vue, and HTML with Tailwind CSS for use in Claude Code and Cursor.
7d ago
Teaching AI to Run with the Turbines
Sponsored article on AI deployment in industrial energy operations, emphasizing governance and human-augmentation over technical details.
7d ago
Show HN: Visual Knowledge Canvas for Learners
LLM-powered visual knowledge management tool for learning. Aggregates sources, answers questions with context, branches conversations, analyzes videos and research papers.
7d ago
Scientists decry conference's use of hidden prompts to snare AI peer reviews
Conference adds hidden prompts to catch peer reviewers using AI for reviews. Raises trust concerns about detection methods.
7d ago
Could the next great novel be written by AI?
Literary discussion on AI-generated novels. Linguists and authors reflect on ChatGPT's impact on fiction writing.
7d ago
Show HN: AI Video Detector – check whether a video may be AI-generated
Tool to detect AI-generated videos. Limited technical details provided.
7d ago
Syscall: Ring ZERO assembly puzzle game for those who are tired of agentic AI
Assembly language puzzle game set in retro BBS environment. Not AI-related despite title reference.
7d ago
Show HN: Qpilot – AI agent runs plain-text manual test cases in a real browser
Qpilot: AI agent that executes plain-text manual test cases in real browser. Supports Claude, OpenAI, Qwen, Ollama, vLLM.
7d ago
Show HN: An MCP server that gives your AI assistant write access to /etc./hosts
LockIn: MCP server enabling AI agents to block distracting websites via system hosts file. Works with Claude, ChatGPT, Cursor.
7d ago
Show HN: ASMLings – Rustlings-style exercises for Intel 8086 assembly
Open-source download manager written in Rust and Flutter as alternative to Internet Download Manager.
7d ago
Show HN: Self hosted excalidraw workspace with storage
Chrome extension that generates multiple-choice quizzes from webpage content with adjustable difficulty and question count.
7d ago
Study: Universities must rethink how they prepare students for an AI world
University study on rethinking education for AI era. Emphasizes critical thinking and ethical judgment skills.
7d ago
Carbon Engine – open-source tech powering EVE Online
Open-source game engine technology powering EVE Online with incomplete documentation.
7d ago
Intent-addressable code for AI coding agents
Causari: Tool recording every AI agent action on codebases—prompts, model used, files read, reasoning. Intent-addressable code.
7d ago
Show HN: Autosynth – generating synthetic data with strong/weak model filtering
LLM-based synthetic data generation tool using weak/strong model filtering, inspired by Meta FAIR's work, with domain-agnostic plugin architecture.
7d ago
AB 1856: CA Exempts Open Source, Still Expands Age-Gating
Policy analysis of California legislation (AB 1856) regarding age-gating and open-source software exemptions.
7d ago
Show HN: Forge – A JavaScript runtime built on Mozilla SpiderMonkey
JavaScript runtime built on Mozilla SpiderMonkey engine with limited documentation and incomplete feature set in preview stage.
7d ago
Show HN: I built LibreYOLO, an MIT-licensed YOLO library
Open-source MIT-licensed YOLO computer vision library built to provide an alternative to proprietary real-time vision solutions.
7d ago
Ask HN: Which AI model do you use for what?
Discussion post listing which AI models users employ for different tasks.
7d ago
AI Poisons Creativity [video]
Headline only with no content provided.
7d ago
Don't Train the Model, Evolve the Harness
Headline only with no content provided.
7d ago
Fable 5. Safety Taken to an Extreme
User tests Claude Fable 5 and finds its safety guardrails overly broad, flagging routine programming and biology work inappropriately.
7d ago
The LLVM Compiler Infrastructure
Headline only with no content provided.
7d ago
Godot cracks down on "vibe-coded" pull requests
Godot game engine adopts policy restricting AI-generated pull requests, citing quality concerns and vague understanding from AI-assisted contributors.
7d ago
How AI models would vote in Sweden
Analysis of how major AI chatbots voted in Swedish election test, noting system prompts and safety layers affect outputs beyond base model.
7d ago
Varela: Neuromancer-inspired 3D self-mutating coding harness
Varela is a self-mutating AI agent harness in JavaScript with WASM sandbox, multi-agent orchestration, and model routing to Anthropic/OpenAI/OpenRouter. Rewrites own code while running, learns from wins/failures.
7d ago
Show HN: High performance command guard and policy enforcement for Agents in Zig
Orca: Safety layer for autonomous AI agents in Zig, enforcing policies to prevent dangerous operations like data deletion and credential leaks.
7d ago
Show HN: Crew – Let Claude Code agents talk to each other
Crew: Developer tool enabling multiple Claude Code agents to collaborate on same codebase by sharing context and messaging without branching.
7d ago
I am dreading our LLM-written incident report future
Opinion on risks of LLM-generated incident reports. Discusses potential and concerns without technical depth.
7d ago
NERM – a tamper-evident audit log that proves itself. Run it yourself
NERM: Open-source tamper-evident append-only audit log using hash-chaining and SHA3-256. Infrastructure tool, not AI/ML focused.
7d ago
Agentic coding notes from Galapogos Island
Personal experience using AI agents for coding tasks, discussing agent behavior and debugging approaches with GPT-5. Anecdotal insights.
7d ago
What the AirCon Debate Says About Britain's Climate Insanity [video]
Title-only stub about UK air conditioning policy. Off-topic.
7d ago
FEOM – Windows GUI automation at 8ms, no GPU needed
FEOM: Open-source Windows GUI automation framework for AI agents with 8ms latency, eliminating vision token costs for deterministic OS operations.
7d ago
Show HN: Void test: 6 frontier LLMs go silent on "Be silence." Live proof
Claims to test six LLM models with proprietary method. Non-standard model names and unclear methodology reduce credibility.