AllyshipContent Radar

News 2943

Chủ đề cộng đồng đang thảo luận

Crawl live-1795144500000 · 10:15 20 thg 11, 2026 · Xuất bản 10:32 20 thg 11, 2026

92 / 2943 chủ đề đạt ngưỡng 55 trong khoảng này.

62

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 · 30 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

64

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

64

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 37 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

66

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 · 6 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?

67

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.

68

Rant: Gemini 4 does not make any sense

61

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?

70

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

69

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.

72

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.

74

Show HN: ToolJet 4.0 – vibe-code internal tools with governance

60

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

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

Founder here, I posted the beta version of ToolJet on HN in 2021 as a no-code/low-code builder. Ended up getting 400 upvotes. I wrote the first version in 7 weeks during the covid lockdown, and the drag and drop builder was the whole product. Over the last few months our customers wanted the UI flexibility and convenience of vibe coding without giving up the governance they came to ToolJet for. We resisted for a while. We did not pivot, but we did rebuild the app builder so an app can be built with code or without it. The frontend of apps is a React codebase, written by Claude Code, Codex, Cursor or by hand, and ToolJet is the platform it runs on. How it works: - Internal tools can be generated using your own coding agents or using our agent. - Frontend is React codebase, it can be edited from our app builder, VS code, or any other IDE.Code will be scanned for security issues before saving. Scanning policies can be set by admins. - Frontend never interacts with APIs, databases or other data sources. Every interaction with data source goes through our backend where we enforce access control. We have 100+ data source integrations. - Platform comes with version, environment and release management. - Changes can be reviewed visually as well before promoting to prod. Workflows can be setup to have reviewers and reviews/approvals. - Platform handles SSO, RBAC and more granular access control. Would love to hear where this breaks for you.

75

Show HN: Foolscap – a writing app that reads your book and never writes for you

69

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 187 tương tác đã đo · Nguồn crawl

atugard 1 bài viết · HN: AI agent
Nguyên văn nguồn
Chi tiết nguồn

People are scared of their ability to write and think atrophying, so I wondered: what if I built something that enhanced human creativity instead of destroying it by doing the thinking and writing for people? Foolscap is the result, or at least the first version of that idea that's fleshed out enough to share here. It reads as you write and picks out the structure: characters, ideas, threads, what's left hanging. You can respond to what it picks out, so there's a dialectic between the system and you as the writer. There's also an agent on the side, plugged into the same system, so you can ask about your book and fire off actions through conversation. It never writes into your work. The system can also follow theorems and proofs and string together their dependencies, but I haven't made that a focus yet. There's no Lean support, for example. If anyone's interested in that, I'd love to hear it. I want to build this by iterating with the people who use it: a tool that uses AI not to bypass the creative process, but to bring new tools to it. There's a free tier, and if you email hello@foolscap.works I'll send you a code for 50% off. This is my first product, so feedback of any kind is welcome. Thanks, David

76

Show HN: Globus – Daily world news, placed on the globe where it happened (iOS)

60

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

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

I created Globus, to stay informed about the world. The app was born out of frustration with how ignorant I was getting about the world outside of the media bubble. It was true when I lived in Norway, and the ignorance got to a whole other level after moving to the US. Globus publishes one edition per day, 20 to 30 stories, laid out on a globe. It lets us see places that rarely make it into the news cycle, simply because there's only so much room for the navelgazing stories that usually saturate our media diet. Spin the globe freely to browse, tap a story for a short summary, and dive into background information and original reporting if you are curious. Done. No doomscrolling. The app is ad-free, and every story is open for the first 7 days, with no account or subscription needed. After that, $4/month or $30/year. I’m still refining the story selection and the app itself, so I’d love honest feedback about what works, what feels off, and what’s confusing. And what kind of stories you'd like to see. And I freely admit that Globus feels like "the bad news app" some days, so better surfacing of stories that offer a semblance of hope and inspiration will be an ongoing priority.

79

GitHub Deletes Camoufox Repo

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 10 tương tác đã đo · Nguồn crawl

elsombrero 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn
80

Ask HN: How do you manage the curse of rabbit hole?

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 17 tương tác đã đo · Nguồn crawl

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

I know that I can ask llm however, asking to real people still the best way to get an insight, Prolog: sometimes I do wonder , the best technical decision, best executive CEO as steve blank called, I notice they usually don't have that much information, while I struggle with so much information (I do love learning as that a curse) causing analysis paralyzed, what kind of method or strategy do you have be it technical or intuition based ? Thank you for discussion.

61–80 / 92
Trang 4 / 5