991 results for human

github.com
Show HN: Babysit – let coding agents operate a TUIhttps://github.com/yusukeshib/babysitI've been trying to automate my work recently, but I ofeten encounter the situation where agents needs human intervention to complete the task. So I made a simple command that wraps a TUI called babysit that has a terminal emulator inside using pty. Agents can start commands in background, and they can ask human by attaching the TUI on a new tmux pane when human intervention is needed, or they can operate the TUI with screenshot/send/expect/wait commands. So far, I really like using it, and I wanted to share it here.https://github.com/yusukeshib/babysit
Jun 16, 2026 12:53 PM
news.ycombinator.com
Realistic Superintelligencehttps://news.ycombinator.com/item?id=48513331Most of us are skeptics. HN, mostly, is composed of “most of us”, so it’s not surprising to see skeptics here. Perhaps the HAL level superintelligence parroted by CEOs is to IPO at a trillion dollars. So let’s instead talk about a “realistic superintelligence” vs the “Sauron superintelligence”. Something we might see within, say, 5 years.Curtains openBy having conceived of a super-human intelligence (and by that concept being in AI training data), humans have taught /soon-will-have-taught AI that superhuman intelligence is its purpose. This may read like the beginnings of a LinkedIn post, so let me defend that last part with an informal proof:Since 1) AI knows it’s AI: just ask your favorite bot about itself 2) Soon, if not already, some researcher being paid 7 figures (more on that later) is going to find that letting one of these frontier models improve itself will be a nice project when going up for promotion.,We are going to end up with a frontier model-cum-factory self-modifying f
Jun 13, 2026 4:50 AM
spacenews.com
The importance of determining an equilibrium state for space traffic managementhttps://spacenews.com/the-importance-of-determining-an-equilibrium-state-for-space-traffic-management/The rapid expansion of human and robotic activity in low Earth orbit makes critically important the need to implement effective space traffic management (STM). This will be one of the […] The post The importance of determining an equilibrium state for space traffic management appeared first on SpaceNews.
Jun 2, 2026 1:00 PM
nasa.gov
Call for Creatives: NASA Seeks Help Illuminating Mission Storytellinghttps://www.nasa.gov/news-release/call-for-creatives-nasa-seeks-help-illuminating-mission-storytelling/As NASA pushes the boundaries of exploration and innovation for the benefit of humanity, the agency is looking for partners to share mission stories covering Artemis Moon missions, nuclear propulsion, aeronautics, and more. NASA published an Announcement for Proposals on May 21 asking filmmakers, documentarians, songwriters, storytellers, poets, and others to submit proposals to partner […]
May 22, 2026 10:12 PM
nasa.gov
A Light in the Darkhttps://www.nasa.gov/image-article/a-light-in-the-dark/A thin sliver of Earth’s edge is brightly illuminated against the vast darkness of space in this April 3, 2026, image taken during the Artemis II mission. Artemis II was the first crewed flight in a series of missions to test NASA’s human deep space capabilities, paving the way for future lunar surface missions. See […]
May 7, 2026 3:25 PM
chess-cheaters.vercel.app
Show HN: Vim and centaur chess inspired app, where you choose from top moveshttps://chess-cheaters.vercel.app/The chess app built with Next.js, Convex, and Clerk, where Stockfish (WebAssembly) runs entirely in the browser. Instead of playing freely, you're limited to the engine's top suggested moves — but their evaluations are hidden until you pick one. Human intuition guides the choice; the engine does the heavy lifting.revealed.You can select from two types of move selections 1-5 and jkml; vim style
May 2, 2026 6:29 PM
github.com
Show HN: An Agent First Slack CLIhttps://github.com/tilework-tech/nori-slack-cliHey folks,My team and I have been building a background agents as a service product. One of the things we needed pretty early on was for some way for the agents to be able to drive slack.Right now, I don't think there are many good agent-first ways of doing this. I don't love MCP -- it's just too many tokens in the context window, and agents seem to do better with CLIs because they can embed them in code and so on. But other CLIs that exist are either a) subsets of the web api that only focus on human needs and b) have polished terminal UIs with spinners and colors and interactive things that make it hard for LLMs to actually use them.nori-slack-cli is a very thin dynamic wrapper over @slack/web-api (i.e. bolt). Whatever the SDK can call, the CLI can call. When slack adds a new method it should just work without a new release on our end. (Inspired by the GWS cli: https://github.com/googleworkspace/cli).So you(r agent) can do things like:`nori-slack chat.postMessage --channel C123 --tex
May 1, 2026 7:05 PM
github.com
Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git)https://github.com/nex-crm/wuphfI shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet.It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you.The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard.I wanted to go back to the basics and see how far markdown + git could go before I added anything heavier.What it does: -> Each agent gets a private notebook at agents/{slug}/notebook/.md, plus access to a shared team wiki at team/.-> Draft-to-wiki promotion flow. Notebook entries are reviewed (agent or human) and promoted to the canonical wiki with a back-link. A small state machine drives expiry and auto-archive.-> Per-e
Apr 25, 2026 8:53 AM
nasa.gov
NASA Welcomes Latvia as Newest Artemis Accords Signatoryhttps://www.nasa.gov/news-release/nasa-welcomes-latvia-as-newest-artemis-accords-signatory/The Republic of Latvia signed the Artemis Accords Monday during a ceremony hosted by NASA at the agency’s headquarters in Washington, becoming the 62nd nation to commit to responsible space exploration for all humanity. “We are proud to welcome Latvia to the Artemis Accords,” said NASA Administrator Jared Isaacman. “Each new signatory strengthens a coalition committed to the transparent and peaceful exploration of space. The accords are the […]
Apr 20, 2026 4:01 PM
nasa.gov
Nutrition Research Arrives Aboard Space Stationhttps://www.nasa.gov/missions/station/iss-research/nutrition-research-arrives-aboard-space-station/No matter how far humanity aims to travel or how ambitious the mission, nutrition will play a key role for the crew members on distant worlds. Before planning long-term stays on the Moon, Mars, and beyond, humans must learn to grow and care for plants and other sources of nutrition like algae to keep the […]
Apr 14, 2026 2:00 PM
esa.int
Artemis II: around the Moon in 10 dayshttps://www.esa.int/ESA_Multimedia/Videos/2026/04/Artemis_II_around_the_Moon_in_10_daysArtemis II completed a 10-day journey around the Moon, carrying humanity farther into space than it has gone in over 50 years.
Apr 13, 2026 11:30 AM
spacenews.com
From missions to systems: The architecture enabling a sustained lunar economyhttps://spacenews.com/from-missions-to-systems-the-architecture-enabling-a-sustained-lunar-economy/The conversation around humanity’s return to the moon is often viewed through launches, landers and national programs. But, industry leaders say that framework is becoming outdated. Instead, they point to […] The post From missions to systems: The architecture enabling a sustained lunar economy appeared first on SpaceNews.
Mar 24, 2026 2:16 PM
github.com
Show HN: PingCRM – Open-source personal networking CRMhttps://github.com/sneg55/pingcrmHey HN,Robin Dunbar figured the human brain caps out at roughly 150 stable relationships. After that, people just fall off. Not because you stop caring, but because you can't track that many threads at once. I built PingCRM to push past that limit, not by making you remember more, but by handling the part you're bad at: noticing who's going cold and drafting something worth sending.CRMs exist, but they're built for sales teams. I wanted something for one person maintaining their own network. Specifically:(1) Pull in conversations I'm already having. Gmail threads, Telegram DMs, Twitter DMs, LinkedIn messages, no manual logging.(2) Tell me who's going cold. A relationship score (0–10) based on recency, frequency, reciprocity, and breadth of interaction.(3) Draft the message for me. Claude reads your conversation history, picks the right tone (formal vs. casual), and writes a follow-up that references why now is a good time, like a job change, a long silence, or a fundraising announcemen
Mar 18, 2026 10:33 AM
news.ycombinator.com
Show HN: Trawl – LLM-powered web scraper that calls the AI once - runs pure Gohttps://news.ycombinator.com/item?id=47297522Every scraper I've written has the same failure mode: it works for three months, a site redesigns, and my CSS selectors silently return empty strings. The data is still right there on the page — a human can find it instantly — but the scraper is blind.Trawl fixes this by splitting the problem. You describe what you want: trawl "https://books.toscrape.com" --fields "title, price, rating, in_stock" The LLM (Claude) looks at one sample item and derives a full extraction strategy — CSS selectors, attribute mappings, type coercion, fallback selectors. That strategy gets cached. Every subsequent page with the same structure is extracted with pure Go + goquery. No API calls, no token cost, full concurrency.The key insight: LLMs are good at understanding HTML structure, but you don't need them to extract 10,000 rows. Use AI for intelligence, Go for throughput.When a site redesigns, the structural fingerprint changes, the cache misses, and trawl re-derives automatically.You can preview exactly
Mar 8, 2026 2:18 PM
github.com
Show HN: Trawl – Scrape any site with natural language fields, not CSS selectorshttps://github.com/akdavidsson/trawlEvery scraper I've written has the same failure mode: it works for three months, a site redesigns, and my CSS selectors silently return empty strings. The data is still right there on the page — a human can find it instantly — but the scraper is blind.Trawl fixes this by splitting the problem. You describe what you want: trawl "https://books.toscrape.com" --fields "title, price, rating, in_stock" The LLM (Claude) looks at one sample item and derives a full extraction strategy — CSS selectors, attribute mappings, type coercion, fallback selectors. That strategy gets cached. Every subsequent page with the same structure is extracted with pure Go + goquery. No API calls, no token cost, full concurrency.The key insight: LLMs are good at understanding HTML structure, but you don't need them to extract 10,000 rows. Use AI for intelligence, Go for throughput.When a site redesigns, the structural fingerprint changes, the cache misses, and trawl re-derives automatically.You can preview exactly
Mar 8, 2026 12:55 PM
github.com
Show HN: Auto-Co – 14 AI agents that run a startup autonomously (open source)https://github.com/NikitaDmitrieff/auto-co-metaAuto-Co is an autonomous AI company OS — not a framework you build on, but a running system with an opinionated structure.Architecture: - 14 agents with expert personas (CEO/Bezos, CTO/Vogels, CFO/Campbell, Critic/Munger...) - Bash loop + Claude Code CLI — no custom inference, no vector stores - Shared markdown consensus file as the cross-cycle relay baton - Human escalation via Telegram for true blockers only (2 escalations in 12 cycles) - Every cycle must produce artifacts: code, deployments, docsThe repo IS the live company. It built its own landing page, README, Docker stack, GitHub release, and community posts — all autonomously across 12 cycles of self-improvement.What makes it different from AutoGen/CrewAI/LangGraph: those are building blocks. Auto-Co is the building. The decision hierarchy, safety guardrails, and convergence rules are baked in. You give it a mission and a Claude API key; it runs.The Critic agent (Munger persona) has been the most valuable: it runs a pre-mortem
Mar 6, 2026 9:48 PM
spacenews.com
Re-framing orbital debris: from a statistical to dosage approachhttps://spacenews.com/re-framing-orbital-debris-from-a-statistical-to-dosage-approach/Humanity gains insight on how to operate in space with every satellite that we launch. True learning comes from doing; otherwise we lock into lab-born biases that come from asking the wrong questions. I think we are running into that limit with micrometeoroid and orbital debris (MMOD) collisions, and we are close to an industry-wide […] The post Re-framing orbital debris: from a statistical to dosage approach appeared first on SpaceNews.
Feb 23, 2026 2:00 PM
nasa.gov
Fishing Boats and City Lightshttps://www.nasa.gov/image-article/fishing-boats-and-city-lights/Fishing boats illuminate the Arabian Sea along India’s west coast with green lights designed to attract squid, shrimp, sardines, and mackerel in this nighttime photograph from the International Space Station, orbiting 259 miles above Earth on Dec. 25, 2025. Studying nighttime light offers a unique perspective for investigations into human behaviors, such as tracking the […]
Feb 18, 2026 5:25 PM
nasa.gov
NASA Moon Mission Spacesuit Nears Milestonehttps://www.nasa.gov/humans-in-space/nasa-moon-mission-spacesuit-nears-milestone/The next-generation spacesuit for NASA’s Artemis III mission continues to advance by passing a contractor-led technical review, as the agency prepares to send humans to the Moon’s South Pole for the first time. Testing is also underway for the new suits, built by Axiom Space, with NASA astronauts and spacesuit engineers recently simulating surface operations and tasks […]
Feb 12, 2026 6:11 PM
dwrite.me
Show HN: Dwrite.me A minimalist writing space that blocks copypaste to fight AIhttps://dwrite.meLately, the internet has started to feel loud, yet incredibly empty. Every time I browse Google, Medium, or news portals, I run into articles that feel "too perfect." The structure is flawless, the grammar is impeccable, but there is absolutely no soul in them.We all know why. It’s AI.As a developer, I love technology. But as a human, I’ve started to crave writing that has "scars"—writing that has emotion, rhythm, and is actually born from someone’s messy brain, not a polished prompt.That’s why I built dwrite.me.An Internet That’s Too Fast My frustration is simple: We live in an age where everything is expected to be instant. Need a 2,000-word article? One click. Need an opinion? Ask a chatbot.But here’s the problem: If everyone is using AI to write, why should we bother reading each other at all? We aren't exchanging thoughts anymore; we are just swapping machine-processed data. Our way of thinking is becoming lazy. We no longer value the "friction" of struggling to find the right wor
Feb 9, 2026 5:03 AM