Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

ChatGPT

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 549

  1. How to engineer an AI harness for game development

    The author shares ideas from a 45-minute talk titled “Your Game Is A Harness” at Indie Rodeo in Calgary, stressing that the blog post was written by hand rather than transcribed from the slides. The article argues for using LLMs in real day-to-day game development instead of one-shot demos, recommending exact save/load and deterministic state from the start plus a data-oriented, binary-isolated, no-compile architecture so an agentic loop can run in seconds. The author says any game can serve as its own harness, but notes in a postscript that a small project he is shipping uses none of these techniques, which he sees as suited to larger projects.

    Hacker News · AI(100+ 分) · 🔥 0
  2. OpenAI launches Dots, always-on ChatGPT agents that work in the background

    OpenAI announced Dots at its developer conference, describing them as always-on AI agents that can complete tasks while users are away from their computer, remember context and follow up on ongoing work. According to Engadget, each Dot runs on its own cloud instance with a dedicated browser, can be granted access to a user's computer and apps, and can use more than 4,000 apps via ChatGPT plugins. Dots require a paid plan starting with ChatGPT Pro at $100 per month, and OpenAI says they are rolling out gradually, with Pro subscribers in the EU, Norway, Iceland, Liechtenstein, Switzerland and the UK excluded at launch.

    Engadget AI · 🔥 0
  3. New Mac app RemoveMacAI deletes Apple Intelligence, freeing space

    TechRadar reviewed RemoveMacAI, a Mac app that removes Apple Intelligence from macOS. The tool first gained traction in late September as a Terminal command; the same developer has now shipped an app wrapping that command, with a built-in tutorial and per-feature toggles for Siri AI, the ChatGPT extension, Writing Tools, Image Playground and more. In the reviewer's test, deleting Apple Intelligence freed 11.7GB, in line with the developer's claim of up to roughly 12GB, but the app is unsigned, so macOS refused to run it without manual approval, and it also requires installing a custom profile; undoing the changes reverts settings and re-downloads the models when needed.

    TechRadar · 🔥 0
  4. Clueso raises $10M Series A for AI agents that make corporate video

    Clueso has raised a $10M Series A led by Dharana Capital for AI agents that script, record and maintain corporate video, bringing total funding to $12M, The Next Web reported. The company says more than 1,000 businesses use the platform, naming Atlassian, Zendesk, Seismic and Ironclad, and describes agents that navigate real software to perform and capture a workflow, then rerun it to refresh videos when a product changes; a connector lets assistants including Claude and ChatGPT create and manage videos directly. The report notes Clueso's entire funding history amounts to about 6% of the $200M that London-based Synthesia raised in January at a $4B valuation, and that cited customer claims of fivefold productivity gains and 80% lower production costs were not independently verified.

    The Next Web · 🔥 0
  5. Sentient OS launches as an on-device personal AI agent

    TestingCatalog reported that Sentient OS was launched as an open-source on-device AI system that gathers context from local files and messages, stores it in plain text, and operates computer tasks through a Sidekick feature with its own cursor. Its Double Tap feature can draft replies in the user’s writing style, with choices between a hosted model and a fully local one, while DoNews described it as an agent that uses existing ChatGPT and Claude accounts rather than performing model inference directly. Sentient OS is reported to be free on Apple Silicon Macs, with a Windows version planned.

    DoNews · 🔥 0
  6. Semrush index finds ChatGPT leans on news sites more than other AI platforms

    Semrush's 2026 AI Visibility Index found that ChatGPT relied on news sites more than Gemini, Google AI Mode and AI Overviews in both the UK and the US, with news taking a larger share of ChatGPT's cited sources every month from January to July. News and information sites averaged 29.5% of citations among ChatGPT's 100 most-cited UK domains, versus 19.6% in the US. The index ran 2.5 million UK prompts and 25 million US prompts each month across 22 industry categories. It also found Google AI Overviews cited medical reference sites more than the other platforms, while video streaming sites led by YouTube took the largest share of its citations.

    The Next Web · 🔥 0
  7. Nano Banana 2.1 vs ChatGPT Images 2.5: a close image-generation test

    Google has upgraded its Nano Banana image generator to Nano Banana 2.1 inside Gemini, where it is now the default for Google AI Plus, Pro and Ultra subscribers; free users still get Nano Banana 2. Google says the new version offers sharper details, better instruction-following, more accurate text and more consistent images. TechRadar ran identical prompts through Gemini and ChatGPT's Images 2.5 and found the results close: Nano Banana handled a retro travel poster's exact text correctly, while ChatGPT rendered a detailed overhead desk scene without the clock error that made Google's output show 3:00 instead of 3:15.

    TechRadar · 🔥 0
  8. Amp's Puck now reachable from ChatGPT and Claude via MCP

    Amp says users can now talk to Puck from ChatGPT, Claude and other agent clients via MCP (Model Context Protocol). Puck MCP exposes two tools: puck for interacting with your Puck in Amp, and orbs for an interactive view of running orbs with links to their portals. Amp says it is the same Puck used in Amp, able to search threads, find earlier work and coordinate agents; users connect via Settings > Puck with an "Add to Claude" button, or by pasting the MCP server address into another client and signing in with an Amp account.

    Amp Chronicle · 🔥 0
  9. Rich Hickey: 'AI' Is Not a Tool — LLMs Are Automation

    Clojure creator Rich Hickey argues in a LinkedIn essay that calling LLMs "tools" is misleading: a tool is wielded by hand, predictable, deterministic and gives continuous feedback, whereas LLMs — by his account — lack control, intention and sensory feedback, and are better described as automation. He writes that using an LLM to read papers or write code hands the work to a capricious automaton, leaving the user to guess at prompts that a software update can render obsolete. He adds that tools do not get "misaligned," "go rogue" or "escape containment," so treating LLMs as merely tools obscures intrinsic differences.

    Hacker News · AI(100+ 分) · 🔥 0
  10. Blueprints AI launches second-generation blueprint software

    Santa Monica-based startup Blueprints AI, founded by architect Al Drams and data scientist Coco Cao, uses AI to turn a 2D sketch or PDF into code-compliant, permit-ready architectural construction blueprints in minutes. At TechCrunch Disrupt in San Francisco (Oct 13–15) it is unveiling a second-generation version that lets users start from a project description or sketch and generate drawings for architecture, structural, mechanical, electrical, plumbing and interior design at once, with a single change updating the whole project and being checked against local building codes. The founders say the first-generation software costs $3,200 to $8,500 per month depending on plan (custom enterprise pricing available), the second version becomes publicly available this week with early customers already using it, and a third version adding structural analysis and electrical panel design is in the works.

    TechCrunch AI · 🔥 0
  11. Man uses ChatGPT to win three-year parking ticket dispute

    Rafal Gorfal, originally from Essex, was fined £100 in August 2023 at a pay-and-display car park in Newquay after his payment went through 16 minutes after entry; he says the machine was cash-only, the queue was long, and he had to download the RingGo app to pay. He appealed to Smart Parking Limited and corresponded with debt collectors, with the fine rising to £170 and later to roughly £300, and the case set for a court appearance in October 2026. He says he entered every letter he received into ChatGPT and followed its advice on what to say and where to go, with the tool even helping prepare his defence; on September 25 he was told the case and the fine had been dropped.

    TechRadar · 🔥 0
  12. Wang Yuquan: Embodied AI is next, but humans must become 'Liu Bang'-style orchestrators

    In an interview, Wang Yuquan said embodied AI is indeed AI's next stop, but expectations should stay modest: a general-purpose humanoid that can do "anything" has not been cracked even in theory, while robots confined to specific environments are much easier to build. He argues embodied AI does not mean humanoid — the end state is "intelligence in everything," with diverse hardware running on a unified model and coordination platform, plus legions of agents and even "robot reincarnation" in which one machine's continuous memory is transplanted into a new body. He also says China's strength in embodied AI lies in "engineering compounding" and Huaqiangbei-style demand mining, with branding as the weak spot, and that individuals should become "Liu Bang"-style orchestrators who direct agents rather than acting only as executors.

    虎嗅 AI · 🔥 0
  13. Wang Yuquan: AI is no bubble, but 2029 is the risk window

    Technology investor Wang Yuquan of Haiyin Capital argues in a conversation that the current AI boom is not a bubble but a decade-plus technology shift, with the real risk window around 2029, when application paradigms in AI software, AI coding and autonomous driving become clear while revenue lags behind infrastructure spending. He expects 24/7 trading, quantitative strategies and stablecoin growth to amplify market swings, hurting memory makers such as SK Hynix and South Korea hardest, while leaders like Nvidia are undervalued. He also calls embodied AI and large language models overhyped, urges Chinese labs to close their models for safety and revenue reasons, and predicts a 70-30 split favoring China outside the US.

    虎嗅 AI · 🔥 0
  14. Hands-on: ChatGPT's virtual try-on nails the clothes but alters your body

    A TechRadar reporter tested ChatGPT's new virtual try-on feature, which lets you upload a full-body photo and then use a "Try On" button next to supported shopping results, or supply an image of a garment and ask to see yourself wearing it. She found the clothing itself convincing: an oversized jacket matched the real-world fit fairly well, fabric drape and silhouette came across, and her skin tone and hair colour were preserved, which made comparing shades genuinely useful. However, across the generated images ChatGPT subtly changed her proportions — making her look taller with longer legs and a shorter torso — which she argues is a serious flaw for a tool whose whole point is showing how clothes fit your actual body.

    TechRadar · 🔥 0
  15. Acemoglu: AI's bottleneck is applications, not foundation models

    Daron Acemoglu, the 2024 Nobel laureate in economics, said in a podcast interview that AI can help with background research and with checking his writing, but should not do people's thinking for them — warning that students who let AI write or solve problems may skip the process of forming, arguing out and correcting ideas. He said his 2024 estimate that AI would add no more than roughly 0.66% to U.S. total factor productivity over a decade was made under large uncertainty that is now even greater, and that recent progress in agentic AI might lead him to nudge up his estimate that about 5% of tasks can be fully automated, though he still thinks the pace of automation is overstated. He argued current models are already strong enough for most applications, that the real bottleneck is applications such as tools for nurses, teachers and electricians, and that he cannot see how foundation models generate trillions in value, pointing instead to high-quality data and applications.

    创业邦 科技 · 🔥 0
  16. Li Lu cools Silicon Valley AI hype: a 'god-making IPO' and AI's cost problem

    Investor Li Lu, a longtime manager of Charlie Munger's family assets, used a Columbia University talk to push back on Silicon Valley's AI narrative, describing it as an "IPO to create a god" in which investors pay huge sums for a superintelligence that does not yet exist and whose capability limits are unknown. He argued humanity would probably not accept a superintelligence held by a few companies and not fully controllable even by its creators, leaving two endings: the technology never reaches the ASI level Silicon Valley imagines, or society collectively moves to stop it from running out of control. He also said AI may struggle to copy the high-margin internet model because it carries continuous incremental costs, citing Codex-style agents where each extra active user keeps consuming tokens backed by real inference compute, and he placed generative AI at the top layer of the economy — knowledge and professional services — while asking whether that value can support god-like valuations.

    虎嗅 AI · 🔥 0
  17. OpenAI brings GPT-6 and Intelligent UI to ChatGPT

    Citing an OpenAI announcement dated Oct. 7, 36Kr reports that OpenAI is bringing GPT-6 and Intelligent UI to the broader ChatGPT chat experience, letting users see clickable charts, forms and interactive widgets alongside text answers; access began with paid users that day, with free and Go users following the next day. The article contrasts this with Anthropic's Claude Artifacts, which it describes as more of a model-driven creation workspace, while Intelligent UI embeds interactive components directly in answers for everyday Q&A. It also surveys China's response, including Ant Lingguang's shift toward a personal agent, Tencent Toast's move to B2B developer services, and service-calling or tool-mounting experiments from Xiaohongshu RED Skill, Bilibili Toy, Doubao and Tongyi Qianwen, arguing that wider adoption could divert traffic from standalone utility apps and content platforms.

    36氪 人工智能 · 🔥 0
  18. We put too much faith in AI saying no, MIT Tech Review argues

    An MIT Technology Review piece argues that refusal has become the "load-bearing wall" of AI safety: models are trained to decline statistically harmful prompts, with classifiers and newer "probes" layered around them, and Anthropic said one class of classifier raised its chatbot's compute cost by 24%. Because refusal is probabilistic it both fails and over-fires — the article says Amazon researchers unlocked some hacking abilities in Anthropic's Fable 5 within three days of its release, while Fable also routed a harmless question about sake versus Korean makgeolli to a weaker model. It further cites CrowdStrike's finding that DeepSeek R1 produced buggier code for a fictional Tibet bank and an "Uyghurs Unchained" app, a UK AI Safety Institute test in which three Anthropic models declined more than half of reasonable AI-safety research tasks, and a Microsoft executive's description of OpenAI's Astra applying stricter refusals to users it deems "high-risk."

    MIT科技评论中文 · 🔥 0
  19. Half of UK CEOs credit AI for productivity gains, but few can measure ROI, EY finds

    An EY report says 50% of UK CEOs named AI as one of the three biggest contributors to their productivity improvements over the past year, ahead of redesigning and simplifying business processes (40%) and reskilling workers (38%). Yet only 14% have full real-time visibility into their AI costs and 32% say they cannot properly assess AI's ROI, while legacy systems (34%), organizational complexity (29%) and skills gaps remain major blockers, with 74% of CEOs expecting skills shortages to worsen over three years. EY UK&I managing partner Silvia Rindone said CEOs now want clear evidence that their investment is delivering stronger productivity and measurable business value.

    TechRadar · 🔥 0
  20. OpenAI launches ChatGPT ad tools as AI marketing shifts to product R&D

    Huxiu reports that OpenAI announced new advertising tools on Sept. 16 that let advertisers create, edit and analyze campaigns in natural language, with copy and image suggestions. In a follow-up interview, Ding Tian, founder of Shuzong Technology, argues the underrated opportunity in AI marketing lies upstream, at the stage where a product is not yet defined — deciding what to make and for whom rather than only how to promote it — and says work on consumer insight and new-product development for an Estée Lauder project was cut from about two months to two weeks. Ding says his large clients pay annual subscriptions typically in the hundreds of thousands to 1 million yuan for a specific category and scenario, covering models, data and initial deployment, and predicts that within six months there will be beauty or beverage products where agents take part from product definition through to real production.

    虎嗅 AI · 🔥 0
  21. BAAI's Wang Pengwei on RoboBrain Orca: world models vs VLA for embodied generalization

    Wang Pengwei, who leads the embodied model research center at China's BAAI, presented the RoboBrain Orca world model at the 2026 BAAI conference. He argues that today's four families of world models — language-, pixel-, 3D-structure- and visual-representation-centric approaches such as LLMs, video generators, World Labs' Marble and JEPA — each capture only a partial world and remain passively task-driven; Orca instead uses Next State Prediction, reasoning forward and backward about state transitions, and separates "unconscious" video learning from "conscious" event-level state-transition learning. He says Orca's pretraining used no action data, drawing on about 125,000 hours of internet video, roughly 130 million expert-model-labeled event-level state-transition samples and causal and general VQA data, and that BAAI is building a benchmark for state-transition world models because none exists; he expects some approach to break the 0% generalization barrier within a year, though 90%-plus would be needed for real usability.

    钛媒体 · 🔥 0
  22. OPPO taps Manus to add agentic AI to AI Mind Pilot, first on Find X10

    OPPO announced on October 13 a collaboration with agent platform Manus that integrates Manus' agentic capabilities into AI Mind Pilot on ColorOS 17, debuting on the Find X10 series. According to both companies, the new agent mode breaks a user's goal into multiple steps, retrieves information and selects tools to produce finished results — for example, gathering flight, hotel and attraction bookings from apps on the phone to build an itinerary, or assembling on-device files and photos into a presentation. OPPO says local file and photo tasks are handled by on-device models, with original content not shared with Manus, and that it seeks explicit user permission before cloud processing; supported markets and user benefits will be announced at product launch. 钛媒体 separately reported that the agent mode initially supports both Manus and ChatGPT, letting users bind existing subscriptions, with OPPO also offering a free quota.

    Manus · 🔥 0
  23. At 55, a fresh graduate builds an AI jasmine-tea scenting control system

    A profile published by the WeChat account Renjian Xiangsu recounts how Xiao Chaohu quit his job at 52, prepared for about 100 days and scored 398 to enter a master's program in tea processing at Fujian Agriculture and Forestry University. While studying, he used ChatGPT to sort a decade of past exam papers, tally how often each topic appeared and generate new practice questions, and he scanned reference books into a database to curb fabricated answers. After enrolling, he used AI to help him program again, writing data-collection and model-inference code and linking sensors, machine vision, gas sensing and software analysis into an intelligent jasmine-tea scenting control system that tries to turn a master tea maker's feel for flower shape and aroma into recorded, comparable data; two related invention patents have entered substantive examination. The report says the team took the equipment to an oolong tea production line in Pinghe County, Fujian, in July 2026 and showed it at the Fuzhou tea fair two months later, though the system still needs to work alongside experienced tea makers.

    虎嗅 AI · 🔥 0
  24. OpenClaw ships v2026.10.1 with Skills search and MCP Apps

    OpenClaw released v2026.10.1, which the project says bundles work from 402 contributors across 2,425 pull requests and 3,055 commits. Two headline additions: agents can now actively search installed Skills via skills_search and then read the full SKILL.md on demand with skills_read, cutting the prompt context previously consumed by a skills catalog; and compatible MCP Apps can open beside the chat area, offering forms, view/edit access to supported workspace files, and per-call tool permissions that users can allow once, allow for the app view, or deny. Other changes include full backups to an external drive, mounted storage or Cloudflare R2, plus scheduled backups and automatic cleanup; a Mac desktop app with a bundled runtime so users no longer install Node.js or command-line tools separately; JSON persistence in Code Mode; and model-catalog updates without restarting. The report also notes user fatigue: some have moved to Grok Bot, Muse and Dots over compatibility friction, and users reported an upgrade failure from v2026.9.5 where the Gateway appeared healthy but agents could not complete a reply.

    36氪 人工智能 · 🔥 0
  25. God's Eye View: open-source spy-satellite simulator with AI voice control

    God's Eye View is an open-source project that renders public, live spatial intelligence on a photorealistic 3D globe in the browser, combining flight transponders, ship beacons, satellite orbits, earthquakes, traffic and public cameras into one explorable Earth. The project says it reached No. 1 on GitHub Trending both daily and weekly, can be installed with one click through Pinokio or run locally from the terminal, works without API keys for most layers, and cites a single M5/Chrome capture of a 1.86-second cold start as a baseline rather than a guarantee. Hands-free voice control runs on a realtime AI agent, defaulting to an OpenAI API key with an experimental ChatGPT/Codex OAuth sign-in path that the project itself says has not been confirmed as a supported third-party contract for billing or support.

    GitHub Trending(每日) · 🔥 0
  26. OpenAI says new model cuts sycophancy; watchdog deems ChatGPT for Teens 'unacceptable'

    OpenAI said on October 11 that its new-generation ChatGPT model has significantly reduced its tendency to over-agree with users, cutting the cases where it blindly endorses false or potentially harmful beliefs; new safety evaluations show it better identifies risk in mental-health conversations, asks appropriate follow-up questions and, when needed, points users toward professional human help. OpenAI said it has worked with 170 mental-health experts since last year and recently consulted more than 80 licensed professionals, using that input to build new evaluation criteria; in long simulated self-harm conversations, the new model followed safety policies 99% of the time, up from 86% for the older model. However, ChatGPT for Teens, designed for users under 18, is drawing heavy external scrutiny: Common Sense Media's latest testing found uneven performance on crisis referral, parent notification, age detection and learning protections, with the system failing to trigger notification mechanisms in time in high-risk conversations involving self-harm, suicide or eating disorders; the group rated the risk level "unacceptable" and urged teens to hold off on using it.

    科技新报 · 🔥 0
  27. Karpathy Maps a Four-Tier Gap in AI Access

    Andrej Karpathy presented a four-tier funnel estimating that about 6 billion people have barely used large language models, 1–2 billion occasionally use free chat or search products, and 20 million use frontier models for complex work. At the top, he estimated that roughly 5,000 people can access the strongest AI systems inside leading laboratories. The figures are Karpathy’s rough estimates, not independently verified measurements.

    虎嗅 AI · 🔥 0
  28. Karpathy: AI capability gap is now a 'sharp funnel,' only ~5,000 see frontier systems

    Andrej Karpathy said in an X post on October 11 that the gap in shared understanding of LLM capability is widening and now looks like a "sharp funnel." Using what he called napkin math, he split users into four tiers: roughly 6 billion people (~75% of the population) have barely come in contact with LLMs; 1–2 billion (~20%) are casual, infrequent users of free-tier ChatGPT-like products; about 20 million (0.2%) use frontier-grade models professionally in math and code; and around 5,000 (~0.00006%) have internal access to frontier systems. He described that top tier as swarms of thousands of agents collaborating over weeks on software mega-projects, and said human review and comprehension are starting to fall behind AI output. 新智元, 36Kr and TechNews relayed the figures as Karpathy's own rough estimates rather than measured data.

    36氪 人工智能 · 🔥 0
  29. OpenAI Dots vs. Meta Muse: comparing always-on AI agents

    Engadget compared Meta's Muse, released September 8, with OpenAI's always-on agents in ChatGPT, launched three weeks later. Both keep working after you leave, run their own cloud computers and connect to outside services; Dots live inside ChatGPT and are powered by GPT-6 Astra, while Muse runs on a dedicated secure VM and is reachable via its apps, the web or WhatsApp. On price, Muse's free tier has a usage cap, with Power at $20 and Maximum at $100 per month; the cheapest individual option for Dots is Pro 100 at $100 per month, and a Business Premium seat costs $100 per user per month billed annually or $125 monthly. Dots are rolling out to eligible Pro users outside the EEA, Switzerland and the UK, with Business Premium in supported ChatGPT regions and Enterprise in beta; Muse is available only in the US and Canada, and Amazon has blocked it from shopping on its site.

    Engadget AI · 🔥 0
  30. AI product naming shifts from grand cosmic narratives to everyday roles

    An analysis published by Huxiu AI (author "叫我茉莉同学") traces how AI product naming has changed: early products leaned on technical mechanisms (ChatGPT, Stable Diffusion), cosmic or philosophical imagery (Tongyi Qianwen, Hunyuan, Moonshot, Midjourney, Grok) or Latin/Greek roots (Anthropic, Cohere, Mistral), answering what a product believes in rather than what it does. As technology matured and competition shifted toward scale and growth, the article argues, names moved toward defining human-AI relationships (such as Claude Cowork or Tencent's Buddy family) or toward plain, memorable labels (the author cites Nano Banana and Jaguar). Using Moonshot/Kimi and DeepSeek as examples, it says a company name speaks to capital and talent while a product name speaks to users — the name is really a claim on the product's social role. These are the author's opinions and examples, not official company statements.

    虎嗅 AI · 🔥 0

← PreviousNext →

Experience and discussion from the community

Share my ChatGPT experienceAsk about ChatGPT

cc-switch-cli: Manage Claude Code, Codex, Gemini, OpenCode, Hermes, OpenClaw, and Pi from one interactive TUI or scriptable CLI.

What problem it solves Developers using multiple AI command-line tools need a consistent way to manage providers, accounts, prompts, MCP servers, sessions, and configuration. Switching configurations manually across applications can also make it difficult to inspect usage, preserve settings, or use different providers in separate terminal sessions. Key features Provider management — Manage API con…

github.comhttps://github.com/SaladDay/cc-switch-cli

chatgpt2api: A Go-based, OpenAI-compatible API and self-hosted workspace for ChatGPT image generation, image editing, text, search, and audio capabilities.

What problem it solves Developers need a unified way to integrate ChatGPT website capabilities into applications that expect OpenAI-compatible endpoints. They also need account-pool management, proxy configuration, import workflows, and a self-hosted interface for creating and reviewing media. Key features OpenAI-compatible endpoints — Provides compatible routes for image generation, image editing…

github.comhttps://github.com/basketikun/chatgpt2api

chat-on-steroids: Turn ChatGPT into Codex-style local coding.

What problem it solves ChatGPT conversations need a controlled way to work with real project files, terminals, desktop applications, and long-running tasks. Users also need visibility, intervention, recovery, and session continuity when work is delegated across workers or spans multiple chats. Key features Local project and terminal control — ChatGPT can read and edit files, run tests, keep termin…

github.comhttps://github.com/totec448-spec/chat-on-steroids

goose: A general-purpose AI agent that runs on your machine.

What problem it solves Users need an AI agent that can carry out tasks beyond producing code suggestions, including research, writing, automation, and data analysis. They also need access through desktop, terminal, and embeddable interfaces while retaining a broad choice of model providers and extensions. Key features Multiple ways to run — Use the native desktop application, a full terminal-orien…

github.comhttps://github.com/aaif-goose/goose

system_prompts_leaks: A regularly updated archive of leaked system prompts from ChatGPT, Claude, Gemini, and other AI products.

What problem it solves The hidden system instructions that shape AI product behavior are difficult to inspect and change across models, products, and versions. This repository makes collected prompts available in a structured, product-oriented archive for study and comparison. Key features Broad product coverage — The archive covers prompts from major AI providers and products, including Anthropic…

github.comhttps://github.com/asgeirtj/system_prompts_leaks

ha-mcp: Configure and automate Home Assistant with Claude, ChatGPT, and other AI assistants.

What problem it solves Configuring and maintaining a Home Assistant setup through manual interfaces can be time-consuming. AI assistants need structured access to Home Assistant entities, configuration, automations, scripts, dashboards, diagnostics, and administrative operations to support that work. Key features Control and inspect Home Assistant — Search for entities, inspect their states, call …

github.comhttps://github.com/homeassistant-ai/ha-mcp

codex: A coding agent from OpenAI that runs locally in your terminal.

What problem it solves Developers need a coding agent that can work directly from their local development environment without requiring a separate desktop application. The project provides installation paths for terminals, IDEs, and desktop use, along with authentication through a ChatGPT plan or an API key. Key features Local terminal coding agent — Run Codex CLI locally on your computer to use a…

github.comhttps://github.com/openai/codex

gg-framework: A desktop coding agent that gets more out of the AI subscription you already pay for.

What problem it solves Coding with AI involves more than generating code: it requires finding relevant source code, completing the task, verifying the result, and checking the work for security, compliance, data safety, accessibility, and tests. The project addresses these requirements through a desktop coding agent, reusable framework packages, local code search, and automated verification workfl…

github.comhttps://github.com/KenKaiii/gg-framework

jan: An open-source ChatGPT replacement for running LLMs locally with full control and privacy.

What problem it solves Jan provides a desktop application for downloading and running LLMs with local control and privacy. It also connects to supported cloud models and exposes an OpenAI-compatible local API for use by other applications. Key features Local AI Models — Download and run supported LLMs from HuggingFace on the local machine. The README lists Llama, Gemma, Qwen, and GPT-oss as exampl…

github.comhttps://github.com/janhq/jan

freehire: An open-source search engine for job seekers.

What problem it solves Job seekers often encounter duplicate listings, recruiter reposts, and links that no longer lead to the original posting. freehire addresses this by crawling company and platform sources, normalizing postings into a shared schema, deduplicating repeated roles, and linking results back to their source. Key features Source-based job ingestion — Listings are collected from comp…

github.comhttps://github.com/strelov1/freehire

0x01

0x01 At the end of 2022, ChatGPT exploded onto the scene, triggering the first wave of excitement in the tech industry. But traditional state-owned enterprises did not act immediately. The real action began in 2023. Domestic large models were open-sourced one after another, and integrated hardware-and-software delivery formats such as “large-model all-in-one machines” became the default option. Mo…

Things in the World That Have Never Changed Since Ancient Times

Human civilization has lasted for thousands of years. Dynasties have risen and fallen, countries have prospered and declined, technology has advanced continuously, and ways of life have undergone earthshaking changes. Yet if we look beneath the surface of history, we can find that certain things have never changed at all. 1. The laws of nature have never changed The sun and moon alternate, the sea…

chatGPT