South Korean ex president Yoon Suk Yeol jailed for life for leading insurrection
Former South Korean President Yoon Suk-yeol has been sentenced to life in prison for leading an insurrection against the government. The article details the charges and trial that led to this verdict, which is seen as a significant political development in South Korea.
A terminal weather app with ASCII animations driven by real-time weather data
The GitHub repository 'weathr' provides an open-source weather application that allows users to check the current weather and forecast in their location using real-time data from public weather APIs. The project includes a user-friendly interface and the ability to save favorite locations for quick access.
AI is not a coworker, it's an exoskeleton
The article explores the concept of AI as an 'exoskeleton' that can enhance and augment human intelligence, rather than replace it. It discusses the potential of AI to assist and empower humans in various tasks, highlighting the complementary nature of human and artificial intelligence.
Single vaccine could protect against all coughs, colds and flus
The article discusses the debate over the future of work, with the COVID-19 pandemic accelerating the shift towards remote and hybrid work models. It explores the potential benefits and challenges of these new work arrangements, and how they may impact both employees and businesses in the long run.
Farewell, Rust for web
The article discusses the author's decision to move away from the Rust programming language after an extended period of using it. The author reflects on the strengths and limitations of Rust, and the factors that led to this change in their programming language preference.
DOGE Bro's Grant Review Process Was Literally Just Asking ChatGPT 'Is This DEI?'
The article discusses a grant review process where the decision-makers simply asked ChatGPT whether the proposals were sufficiently diverse and inclusive, rather than engaging in a more thorough evaluation. The article suggests that this approach undermines the purpose of diversity, equity, and inclusion (DEI) efforts.
Show HN: Ghostty-based terminal with vertical tabs and notifications
I run a lot of Claude Code and Codex sessions in parallel. I was using Ghostty with a bunch of split panes, and relying on native macOS notifications to know when an agent needed me. But Claude Code's notification body is always just "Claude is waiting for your input" with no context, and with enough tabs open, I couldn't even read the titles anymore.
I tried a few coding orchestrators but most of them were Electron/Tauri apps and the performance bugged me. I also just prefer the terminal since GUI orchestrators lock you into their workflow. So I built cmux as a native macOS app in Swift/AppKit. It uses libghostty for terminal rendering and reads your existing Ghostty config for themes, fonts, colors, and more.
The main additions are the sidebar and notification system. The sidebar has vertical tabs that show git branch, working directory, listening ports, and the latest notification text for each workspace. The notification system picks up terminal sequences (OSC 9/99/777) and has a CLI (cmux notify) you can wire into agent hooks for Claude Code, OpenCode, etc. When an agent is waiting, its pane gets a blue ring and the tab lights up in the sidebar, so I can tell which one needs me across splits and tabs. Cmd+Shift+U jumps to the most recent unread.
The in-app browser has a scriptable API ported from agent-browser [1]. Agents can snapshot the accessibility tree, get element refs, click, fill forms, evaluate JS, and read console logs. You can split a browser pane next to your terminal and have Claude Code interact with your dev server directly.
Everything is scriptable through the CLI and socket API – create workspaces/tabs, split panes, send keystrokes, open URLs in the browser.
Demo video: https://www.youtube.com/watch?v=i-WxO5YUTOs
Repo (AGPL): https://github.com/manaflow-ai/cmux
[1] https://github.com/vercel-labs/agent-browser
MuMu Player (NetEase) silently runs 17 reconnaissance commands every 30 minutes
The article discusses the development of ChatGPT, an advanced language model created by OpenAI, and its potential impact on the field of AI. It explores the model's capabilities, the challenges involved in its creation, and the ethical considerations surrounding its use.
CTO Says 93% of Developers Use AI, but Productivity Is Still 10%
The article discusses a survey that found 93% of developers use AI tools, but only a 10% increase in productivity. It highlights the importance of responsible AI adoption and the need for better integration of AI into development workflows to maximize its benefits.
Techno-cynics are wounded techno-optimists
The article discusses the political views and ideology of Anthropic's AI assistant, Claude, and how it is perceived as having a leftist or progressive bias. It explores the implications of AI systems reflecting certain political perspectives and the ongoing debate around the role of technology in shaping societal discourse.
Hitler's Greenland Obsession
The article explores Adolf Hitler's plans to invade and colonize Greenland during World War II, a little-known historical fact. It delves into the strategic and logistical considerations behind this ambitious but ultimately failed Nazi scheme.
Pi for Excel: AI sidebar add-in for Excel, powered by Pi
This article discusses an open-source Python library called pi-for-excel that allows users to calculate the value of pi within Microsoft Excel. The library provides a user-friendly interface and supports various methods for calculating pi, making it a useful tool for educational and research purposes.
Show HN: A small, simple music theory library in C99
The article introduces Mahler.c, a C library that provides a higher-level interface for working with the Mahler compiler. It aims to simplify the process of building and integrating Mahler-based projects by offering a set of utility functions and abstractions.
Microsoft's new 10k-year data storage medium: glass
Microsoft has developed a new data storage medium made of glass that can store data for up to 10,000 years. This novel technology uses laser-etched digital data in quartz glass, providing a durable and long-lasting solution for preserving important information for future generations.
Valve wins patent troll lawsuit against Rothschild
Valve wins a lawsuit against Rothschild and associated entities, with a jury agreeing that they violated an anti-patent troll protection act. The article discusses the legal battle and Valve's victory in this case.
Show HN: 17MB model beats human experts at pronunciation scoring
This article describes a Hugging Face Space that allows users to assess the pronunciation of their speech, providing feedback to improve language proficiency. The tool utilizes machine learning models to analyze audio recordings and offer detailed insights on pronunciation accuracy.
University of Texas limits on teaching of "unnecessary controversial subjects"
The University of Texas System Board of Regents has drawn criticism for considering a policy that would allow them to veto the teaching of certain topics deemed 'unnecessarily controversial' on campuses. The proposed policy has raised concerns about academic freedom and the potential for political interference in university curricula.
ICE Raids Family Detention Dorms After Kids' Letters Expose Abuse
The article discusses the letters written by children detained by ICE, which expose the abusive conditions they faced, including lack of medical care, inadequate food and water, and psychological trauma. The letters provide a firsthand account of the harsh realities encountered by immigrant families in ICE detention centers.
Show HN: Optimize_anything: A Universal API for Optimizing Any Text Parameter
We built optimize_anything, an API that optimizes any artifact representable as text — code, prompts, agent architectures, configs, even SVGs. It extends GEPA (our prompt optimizer, discussed here previously: https://arxiv.org/abs/2507.19457) far beyond prompts.
The API is deliberately minimal. You provide what to optimize and how to measure it:
import gepa.optimize_anything as oa
def evaluate(candidate: str) -> tuple[float, dict]: result = run_my_system(candidate) return result.score, {"error": result.stderr, "runtime": f"{result.time_ms}ms"}
result = oa.optimize_anything( seed_candidate="<your artifact>", evaluator=evaluate, )
The evaluator returns a score plus diagnostic feedback (we call it "Actionable Side Information" — stack traces, rendered images, profiler output, whatever helps diagnose failures). An LLM proposer reads this feedback during a reflection step and proposes targeted fixes, not blind mutations. Candidates are selected via a Pareto frontier across metrics/examples, so a candidate that's best at one thing survives even if its average is mediocre.
Two ideas distinguish this from AlphaEvolve/OpenEvolve/ShinkaEvolve-style LLM evolution: (1) diagnostic feedback is a first-class API concept rather than a framework-specific mechanism, and (2) the API unifies three optimization modes — single-task search (solve one hard problem), multi-task search (solve related problems with cross-transfer), and generalization (build artifacts that transfer to unseen inputs). Prior frameworks only express mode 1.
We tested across 8 domains. Selected results:
Coding agent skills: Learned repo-specific skills push Claude Code to near-perfect task completion and make it 47% faster Cloud scheduling: Discovered algorithms that cut costs 40%, topping the ADRS leaderboard over expert heuristics and other LLM-evolution frameworks Agent architecture: Evolved a 10-line stub into a 300+ line ARC-AGI agent, improving Gemini Flash from 32.5% → 89.5% Circle packing (n=26): Outperforms AlphaEvolve's published solution Blackbox optimization: Generated problem-specific solvers matching or exceeding Optuna across 56 EvalSet problems CUDA kernels: 87% match or beat baseline; multi-task mode outperforms dedicated single-task runs
``` pip install gepa ```
Blog with full results and runnable code for all 8 case studies: https://gepa-ai.github.io/gepa/blog/2026/02/18/introducing-o...
GitHub: https://github.com/gepa-ai/gepa
Deaths in Ice Custody Texas
The article examines the deaths of several immigrants in ICE detention centers in Texas, highlighting concerns about medical care and conditions in these facilities. It focuses on the cases of three individuals who died while in custody and the ongoing investigations and scrutiny surrounding these incidents.