AllyshipContent Radar

News 2911

Chủ đề cộng đồng đang thảo luận

Crawl live-1795140900000 · 09:15 20 thg 11, 2026 · Xuất bản 09:31 20 thg 11, 2026

100 / 2911 chủ đề đạt ngưỡng 55 trong khoảng này.

61

Claude solves two open problems in the physics of black holes

88

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 558 tương tác đã đo · Nguồn crawl

Handy-Man, cybermango 1 bài viết · HN: Claude, Anthropic Research (unofficial RSS mirror)
Nguyên văn nguồn
Chi tiết nguồn
64

Show HN: AgentMall – Let your AI agent buy groceries

63

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 22 tương tác đã đo · Nguồn crawl

desilva78_ 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

Hey HN, we’re Nel and Kosi. We noticed personal agents like Instinct, Muse were terrible at buying stuff. Most of the time the checkout would fail. So we built reliable automations for agents to checkout at 9 leading grocery merchants. We grapple with anti bot, logins, OTP codes, and changing checkout structures. Loved revisiting this stuff given our backgrounds sneaker-botting and building computer use models. Honestly full circle haha. It currently works on these sites with ~70% checkout success rate: - Walmart - Albertsons - Ocado - Wegmans - FreshDirect - Best Buy - Instacart Our goal is to hill climb to 90%+ across each. Test keys are free and run the real flow without placing an order. New accounts get 10 free completed orders. https://docs.getagentmall.com/quickstart

65

Launch HN: Onlook (YC W25) – An open-source developer tool for designers

69

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 153 tương tác đã đo · Nguồn crawl

D_R_Farrell 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Hey HN, I'm Daniel, founder of Onlook ( https://github.com/onlook-dev/onlook and onlook.com). Onlook is a desktop app that puts a canvas on top of your real codebase, letting you design directly in code with the agent you already use. Over 25,000 designers and developers have supported the project, 100+ have contributed, and it's been the #1 trending repo in the world twice. We just rebuilt the entire product as an agentic design tool, and open-sourced it to the community. Here’s a demo video: ( https://youtu.be/BogcYWf4siM ) If you're an engineer, traditional engineering tools are largely built for convergence, whereas designers tend to explore and diverge on ideas. Onlook gives designers a familiar canvas while managing all of the dev processes that get between them and making mind-blowing designs in code. Designers can work on a multiple simultaneous worktrees that run on the real app locally, and every change lands as a PR you can review or throw away, so there aren’t mockups to rebuild. We built Onlook because we believe there needs to be a developer tool that works the way designers do. More and more, designers are expected to work in code. Designers think by seeing, drafting, arranging variations, using references, and remixing ideas. That’s why the canvas has been the signature feature of design tools because it genuinely is useful for how messy the creative process is. Most of the challenge of using engineering tools for design work is that the first half of starting a project often takes mental bandwidth in of itself (What branch am I on? What page was that last exploration on?) and the second half is constrained by configuring your coded design to present itself (prompting design tools on top of what you’ve built or making temporary navigation for that specific state). Some of you may remember our earlier Show HNs (July 2024: https://news.ycombinator.com/item?id=40904862 , August 2024: https://news.ycombinator.com/item?id=41390449 , May 2025: https://news.ycombinator.com/item?id=44127653 ). Since then, we built a web version (too early), then a Storybook-native build (a mistake). We noticed that our desktop product from July 2024 was still getting hundreds of downloads a month despite zero promotion, so we decided to rebuild it for the new era of designers working in code. How it works… Onlook shines at exploring tons of ideas at once. Ask it to lay out every flow in your product, show every state of a component, or riff on ten versions of one screen. Your designs all show up side by side on an infinite canvas, with each frame as a real webview running your actual app with real data. Not as a mockup, but the real deal. When we built this editor, we had an epiphany that it could be a new kind of IDE for design. Design tools used to be limited to a proprietary setup or closed schema, but now you can push and pull the medium of code to get whatever result you want, so why not give agents an infinite canvas of browsers and see what they do? It turns out, the agents can figure out how to better present coded work by adjusting the urls of browser frames and arranging and resizing them on the canvas. The concept is simple, but it requires a lot of product thinking. For example, because all of the frames on the canvas share a single browser session, and Chromium only allows six connections per host per session, ten frames of the same app end up fighting over limited connections. So, we had to plan around that, and there are still tons of things we need to do to make the canvas ultra performant. Onlook is an Electron app where you can import a repo from GitHub or upload a local folder. Then, Onlook creates a git worktree, starts your dev server, and has the agent sort out missing dependencies or other requirements. You never open a terminal and everything the agent does is a normal git diff that can go to GitHub as a PR. We inject a small script into each frame that draws selection outlines and reads the page, so that way you can click an element, say "make this a card layout," and the agent knows exactly what "this" is. This time we didn't build our own agent. Onlook runs Claude Code or Codex on your own subscription, and we turn whatever the agent emits into one typed event log and draw the UI from that in our own chat interface. On top of that we give the agent a bespoke set of design-specific tools, from arranging frames on the canvas, to making suggestions, to generating multiple iterations of a selection – which is especially useful because the agent decides how to get the app into a state that you need based on your prompt. We also have our own Artifacts which are quick HTML sketches that live in the editor, but outside your repo. They’re almost like components in other design tools in that they can be carried and edited across every project but are detached from the project with no network access. As an example, you can ask the agent to turn your interface into an Artifact, and use it as a reference for another exploration, or download it as HTML and send it to a coworker as an interactive export of something you have in progress. I frequently go back to the artifacts I’ve made as visual snippets when I need new ideas or need to borrow something that’s already been built. The desktop editor is free (you can download it from our website at onlook.com) and open source under Apache-2.0, and we'll eventually offer a paid cloud product for teams. We'd love to hear which repos work and which don't, what you try to do on the canvas, and what's missing. We’re so excited for this to be a new way for designers to work in code! The Onlook team (Joel - thebrubaker and Kris - krisodd), and I will be here all day!

66

From Static to Current

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 8 tương tác đã đo · Nguồn crawl

whakim 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn
68

Show HN: Dayfile.app – Append-only log for your scripts and agents

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 6 tương tác đã đo · Nguồn crawl

gilad 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Hi HN, I'm Gilad. dayfile.app is a "git log for scripts and agents", with ordered history, append-only logging as foundational characteristics. The service is currently in beta, AGPL-licensed. As I was looking at various ways to record and retrieve a day's to-dos, automation and operational outputs (update successes and failures), the idea of a running event log. dayfile.app's primary use case is DevOps tracking and event logging. Building this, I've emphasized simplifying posting - one HTTP request with a title and optional tags (used for filtering when reading the log), AI access via MCP server (an assistant can read, post or close to-dos) and self-hosting as a first-class citizen (`pip install dayfile`, SQLite database is local in this mode). A demo is available at https://dayfile.app/demo . If using the cloud service and after generating a write token on the site, an example of posting an entry would be: curl -X POST https://USERNAME.dayfile.cloud/events \ -H "Authorization: Bearer WRITE_TOKEN" \ -H "content-type: application/json" \ -d '{"title":"Nightly backup finished","tags":["backup"]}' To read back (filtering using tag): curl -H "Authorization: Bearer READ_TOKEN" \ "https://USERNAME.dayfile.cloud/events?tag=backup&within=7d" or paste https://USERNAME.dayfile.cloud/t/READ_TOKEN/f/backup.atom into a feed reader (you need to create a feed called `backup`). What a local file can't do is notice something didn't happen - this is the heartbeat. dayfile.app can be configured to create an event if no associated event arrives. Imagine a backup which didn't run. A to-do event is created if no evidence of a successful backup shows up within a certain period. When the backup reports again, dayfile closes the associated to-do. Current limits: logs are not end-to-end encrypted, sign-in is via GitHub only, the free beta allows 50,000 events and log size of 25MB. Pricing will be sorted out after this launch and as user feedback rolls in. I'd love to hear in the comments on how you'd use it, what would prevent you from doing so, feature requests and suggestions. Bug reports can be submitted as issues on GitHub.

70

GitLab 19.6.0 is out and still vulnerable to Ruby2Shell and NGINX2Root

64

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 29 tương tác đã đo · Nguồn crawl

hoechst 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

What's going on at GitLab? They released their usual monthly release 19.6.0 to their package repos (https://packages.gitlab.com/gitlab/gitlab-ee/ubuntu/jammy/pool/main/g/gitlab-ee/) but did not announce it at all as of 3.5h after release (https://docs.gitlab.com/releases/all-releases.xml, https://docs.gitlab.com/releases/19/gitlab-19-6-released/). But more annoyingly, this release does not address ruby2shell or nginx2root, nor do patches for their older releases exist yet and there's no communication on any of this (that I can find). root@gitlab:~# cat /opt/gitlab/embedded/service/gitlab-rails/VERSION 19.6.0-ee root@gitlab:~# /opt/gitlab/embedded/sbin/nginx -version nginx version: nginx/1.31.7 root@gitlab:~# /opt/gitlab/embedded/bin/ruby --version ruby 3.3.13 (2026-10-23 revision af48f08f21) [x86_64-linux] root@gitlab:~# lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 22.04.5 LTS Release: 22.04 Codename: jammy Multiple MRs were created in their repos 14-15 hours ago, no urgency visible. Heres 2 I found: https://gitlab.com/gitlab-org/omnibus-gitlab/-/merge_requests/10138 https://gitlab.com/gitlab-org/omnibus-gitlab/-/merge_requests/10139

72

Show HN: Watch weight-space programming in action with WebGPU

64

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 36 tương tác đã đo · Nguồn crawl

wsxiaoys 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

I wanted to build a full weight-space programming loop entirely in the browser with WebGPU: let an LLM inspect Qwen3.5-0.8B, edit its weights, evaluate, and repeat. the full loop needed too much VRAM. so I turned it into an interactive walkthrough of a concrete example: editing 0.016% of a model's weights to reduce reasoning loops, no gradient descent. Based on exp8 of “Sparks of Weight-Space Programming.”: https://news.ycombinator.com/item?id=50341174

74

Ask HN: When was the last time you thought "that's bad API design"?

59

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 5 tương tác đã đo · Nguồn crawl

Mitchem 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

I used to be irrationally impressed when I saw good API design and docs. Now I can't remember the last time I sat down and spent meaningful time reading docs for a platform. I've just gotten in the habit of pointing Claude at them or using a service like Context7 for the past year or so. As a consumer, I've realized that I'm not even sure which services I use that have good or badly designed APIs. If you maintain an API, have you changed how you write docs now that the main reader is probably an LLM?

75

Show HN: Openspot – macOS launcher for disposable tools

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 7 tương tác đã đo · Nguồn crawl

tniich 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Hi HN! We're Tony, Kolom and Anastasiia, a small team from Ukraine. Today we are open-sourcing Openspot, our research project on using generative UI in day-to-day work. The idea is simple: generate a tool (spot) for your current task using coding agent, and keep it if you like it or remove it after use if you don't. We are using Openspot daily and really enjoying the possibilities it unlocks. Some examples of spots: - caffeinate, which allows the Mac to work with the lid closed - local file and screenshot search in natural language using EmbeddingGemma 2 - draw on screen during calls or before screenshots - AI agents monitoring - AirDrop, but over the network (using iroh) We built it because of two things: 1. Over the past year, we (and almost every designer and engineer we know) have started making small tools using coding agents. But the DX for macOS applications is very frustrating even for coders, and you have to pay for a developer account to share them. 2. And we kind of miss the days of custom Winamp skins and Twitter clients. That's why every part of Openspot is customizable, so anyone can give it their own look and feel. This is a very early stage. The code is MIT-licensed, and the core will remain free forever. We're sticking to macOS 26+ for now (because of Liquid Glass). Ask us anything, or roast it. Any feedback is very appreciated.

76

Rant: Gemini 4 does not make any sense

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 14 tương tác đã đo · Nguồn crawl

sambejk 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

On November 18th, Google released another model, this one called Neon. Making it the fourth model in just 2 months. OpenAI makes sense: Luna-Terra-Sol-Astra. Moon is smaller than earth, earth is smaller than sun and I can forgive them for not knowing that sun is also a star. Anthropic is even better: Haiku-Sonnet-Opus-Mythos/Fable. Haiku is an extremely short poem, Sonnet is a bit longer, Opus is very long and Mythos is extremely long. Ok, Fable does not exactly really fit in there, but they came up with it after they only had the three models, so we had time to adjust. Also, Claude told me: Fable is basically Mythos with extra safety, and a fable is a story with a moral. Now, I want you to think back to those high school chemistry classes. Which is bigger neon or carbon or hydrogen or argon? Impossible right? The correct answer, hydrogen, carbon, neon, argon, doesn't even match with model capabilities. To make things worse, there is no consistency, they are combining noble gases with other non-metals. You can't even say they went for easy names, helium, is not in there as an example. They really should have gone with just noble gasses: helium, neon, argon and xenon (skipping krypton to not confuse with kryptonite) I'm glad that Google is sort of back in the race, but they should really invest in someone who is not AI-pilled to come up with these names. PS don't get me started on Meta, wtf is a glimmer?

78

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

70

2 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · chưa có số tương tác · Nguồn crawl

Minghe Zhang, Xuetao Kang, Yifei Ming, Yanfei Chen, Han Yu, Yufan Zhuang, Chen-Yu Lee, omarsar0 1 bài viết · arXiv cs.AI, X
Nguyên văn nguồn
Chi tiết nguồn

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat. We introduce GUARD (Grader-free Unsupervised Environment Design [UED] with Adaptive Rule Distillation), a closed-loop framework for reference-free continual harness evolution. Our key insight is to decompose each task into pre-execution self-checks and guide harness updates via directional regret. Each round grades trajectories against these checks, pinning mastered rules while prioritizing newly broken behaviors, and selects among parallel candidate edits by critic-free group-relative fitness. A Soft-HURT gate then promotes an edit only when gains outweigh regressions, scoping specialized fixes to prevent over-triggering and guaranteeing non-regression on its gated buffer. At test time, one frozen harness runs in a single pass. Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.

80

Show HN: Purple Flow – AI-first n8n alternative, 10k+ workflows on 512MB

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 7 tương tác đã đo · Nguồn crawl

leetheguy 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

Hey all! I ran into a wall with n8n - hard and expensive to scale, limited streaming, heavy MCP is confusing for agents. That scaling was becoming more and more critical as I was beginning to build agentic swarms. So I built my own alternative with Elixir and Beam. Been using it in production for almost 2 months. It connects my agent to multiple databases, sandboxes, and APIs. I've even migrated over my most used n8n workflows without a hiccup. I ran some benchmarks and 10,000 concurrent workflows executed in 3 seconds and cost about 330MB of ram (listed as 512 in the case study). Equivalent workflows in n8n took 2GB of ram to run 100. It's roughly 200x the memory efficiency of the usual Node/Python stacks. And while you don't edit the workflows yourself visually, you can see and manage them through a UI, along with credentials that the agent never sees. The workflows themselves are pure TOML. Not as easy as dragging node connectors. But the idea is that AI creates the flows and you can easily understand them. This isn't a shaky demo. I'm using it as my daily driver to create complex multi-agent personas, run research and info gathering swarms, and whatever else my agent needs to get its job done. (it's built more than 70 so far) I have a live working demo on my website that was built by an agent using Purple Flow to connect to my server. The demo itself lets an agent using Purple Flow access live (Adventure Works) data and generate reports, documents, and slides on demand. My agent and I built it in an afternoon. It runs on a lightweight model (to save money for a public demo) with very few hiccups. - Repo: https://github.com/leetheguy/purple_flow - Discord, benchmarks, and demo links in the repo.

61–80 / 100
Trang 4 / 5