AllyshipContent Radar

News 2939

Chủ đề cộng đồng đang thảo luận

Crawl live-1795148100000 · 11:15 20 thg 11, 2026 · Xuất bản 11:32 20 thg 11, 2026

176 / 2939 chủ đề đạt ngưỡng 55 trong khoảng này.

61

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.

62

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

68

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

63

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.

66

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
67

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.

69

Jeveration: System One Models Now Generate

82

5 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 6 tương tác đã đo · Nguồn crawl

Yuhe Liu, Qi Li và 3 nguồn khác 1 bài viết · Hugging Face Papers, X
Nguyên văn nguồn
Chi tiết nguồn

System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image generation. The key challenge is to maintain global consistency. A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. We therefore condition all positions on a shared random state to coordinate parallel predictions, so that each draw yields a different but coherent image. Since the model tends to ignore this state under direct image supervision, we first learn a distribution over discrete image codes to guide single-pass generation. Beyond text-to-image generation, we further unify image-to-image generation and dense prediction within the same architecture, so that one checkpoint supports all three tasks, each in one forward pass. Experiments show that Jeveration generates a 512x512 image in 78 ms, up to 122x faster than existing unified models, while maintaining competitive image quality and dense prediction performance.

71

UltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture Generation

80

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

Jingzhi Bao, Xiaohe Ma và 4 nguồn khác 1 bài viết · Hugging Face Papers, X
Nguyên văn nguồn
Chi tiết nguồn

Generating physically based rendering (PBR) texture maps for a 3D mesh from a single reference image is highly ambiguous, as the observed appearance entangles material identity, surface reflectance, and illumination. While current generative methods produce realistic albedo maps, they still struggle to infer accurate metallic and roughness attributes for relighting. We present UltraTex, a cascaded multi-view framework that moves beyond appearance matching by integrating physical knowledge into multi-view diffusion-based PBR generation. UltraTex first jointly predicts albedo and world-space shading normals to generate more detailed albedo maps, and then predicts metallic-roughness (MR) maps conditioned on the generated albedo, reference image, and material semantic priors. To inject material semantics, a lightweight adapter transforms hidden-layer features of a vision-language model (VLM) into intrinsic material representation tokens, providing part-level knowledge anchors for MR estimation. To model material-light interaction, photometric representation alignment guides intermediate diffusion features toward ground-truth material renderings under controlled lighting. This makes metallic and roughness variations observable through highlight intensity, specular sharpness, and local reflectance contrast, providing stronger guidance for fine-grained material prediction without explicit lighting supervision. Extensive experiments show that UltraTex generates high-quality textures and outperforms existing open-source and commercial methods in visual fidelity, material accuracy, and physical plausibility.

72

llm-gemini 0.38

60

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

Simon Willison 1 bài viết · Simon Willison, X
Nguyên văn nguồn
Chi tiết nguồn

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm-gemini/releases/tag/0.38">llm-gemini 0.38</a></p> <p>Today Google <a href="https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-neon/">introduced Gemini 4 Neon</a>. I <a href="https://simonwillison.net/2026/Nov/12/llm-gemini/">wrote recently</a> about how confusing the pricing for the Gemini 4 series was - Neon has somehow made this even worse.</p> <p>Previously the Gemini 4 lineup was Hydrogen, Argon, and Carbon - where Argon and Carbon were <em>the same price</em>, and Hydrogen was 3/4 of that price now but will be 1/4 of that price when the other two double an 1st December once their initial discount pricing expires.</p> <p>The Neon announcement pretends that Argon doesn't exist. Here's their new image explaining the model line-up:</p> <p><img alt="Comparison table slide titled &quot;Gemini 4 - Our next era of frontier intelligence&quot; with three model columns, Carbon, Neon and Hydrogen, where the Neon column is highlighted with a blue outline. Best For: Carbon - Hardest long-horizon projects and deep research; Neon - Deep reasoning across software engineering, knowledge work, and science; Hydrogen - Speed and efficiency in everyday coding and agentic workflows. Quality (Artificial Analysis Index): Carbon 60, Neon 61, Hydrogen 54. Price ($/1M In / Out (1M flat)): Carbon $4 / $20*, Neon $3 / $15, Hydrogen $1.50 / $7.50. Thinking levels: Carbon - Low, medium, high; Neon - Low, medium, high, xhigh; Hydrogen - Low, medium, high, xhigh. Speed (shown as rocket icons out of five): Carbon 2, Neon 3.5, Hydrogen 5. Subscriptions: Carbon - Google AI Ultra; Neon - Google AI Pro &amp; Ultra; Hydrogen - For Everyone. Availability: Carbon - Gemini API in Google AI Studio (paid), Gemini for business, Google AI Ultra: Gemini app, Google Antigravity, AI Mode in Search; Neon - Gemini API in Google AI Studio (paid), Gemini for business, Google AI Pro &amp; Ultra: Gemini app, Google Antigravity (paid); Hydrogen - Gemini API in Google AI Studio (all tiers), Gemini for business, Gemini app, Google Search, Google AI Pro &amp; Ultra: Google Antigravity (paid). Footnote: *$2 / $10 promo through Nov 30. Dated 18 November 2026." src="https://static.simonwillison.net/static/2026/gemini-4-neon__comparison-graphi.width-2000.webp" /></p> <p>So the lineup now, from most to least expensive, is Carbon, Neon, Hydrogen.</p> <p>Except Carbon is currently half price, so right now Neon ($3/million input, $15/million output) is the most expensive of the three - then Carbon ($2/$10), then Hydrogen ($1.50/$7.50). I guess this will make more sense when Carbon doubles to $4/$20 on December 1st.</p> <p>I ran <a href="https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fabc5dfe18e8d37a46fd09a3dcc18ed5c">some pelicans</a> through the three reasoning levels for Neon - low, medium, high.</p> <p>I dropped Argon from <a href="https://static.simonwillison.net/static/2026/gemini-4-carbon-neon-hydrogen.html">my Gemini 4 comparison grid</a> - here's the new Gemini 4 lineup, where the Neon pelicans do look better than Hydrogen and worse than Carbon:</p> <p><img alt="Comparison grid of nine flat vector-style illustrations of a pelican riding a red bicycle, arranged as a table with three model columns and three thinking-level rows. Column headers: Thinking, gemini-4-carbon, gemini-4-neon, gemini-4-hydrogen. Row HIGH: gemini-4-carbon is the most detailed of all, a pelican in a sailor cap on a red cruiser bike with fenders, chain guard and a wicker basket holding a fish, on a beach promenade with ocean, sun, clouds and distant birds, captioned &quot;40 input tokens, 20,305 output = 20.31 cents · 4m 11s&quot;; gemini-4-neon is a clean, well-proportioned pelican on a simpler red bike on a road with a yellow dashed line and the sea behind, captioned &quot;40 input tokens, 9,691 output = 14.55 cents · 1m 11s&quot;; gemini-4-hydrogen is a plainer pelican on a basic red bike with speed lines, flat green ground and a pale sky, captioned &quot;40 input tokens, 5,311 output = 3.99 cents · 19s&quot;. Row MEDIUM: gemini-4-carbon adds a red striped scarf blowing in the wind plus the sailor cap, cream fenders, a basket and a beach with a rope fence, captioned &quot;40 input tokens, 11,020 output = 11.03 cents · 1m 53s&quot;; gemini-4-neon has a basket with a fish, green hills and a grey road, captioned &quot;40 input tokens, 7,846 output = 11.78 cents · 54s&quot;; gemini-4-hydrogen is a simple pelican and bike on a flat green strip with faint clouds, captioned &quot;40 input tokens, 3,964 output = 2.98 cents · 17s&quot;. Row LOW: gemini-4-carbon is still richly detailed with cap, scarf, basket, a seaside railing and a road, captioned &quot;40 input tokens, 9,153 output = 9.16 cents · 1m 34s&quot;; gemini-4-neon is a simpler pelican on a bike with no basket, on a road edged with grass, captioned &quot;40 input tokens, 4,974 output = 7.47 cents · 43s&quot;; gemini-4-hydrogen is the most minimal, a basic pelican and thin-framed bike over a single green line on a plain pale background, captioned &quot;40 input tokens, 2,996 output = 2.25 cents · 10s&quot;. Overall, detail and polish drop from carbon to neon to hydrogen and, less sharply, from high to low thinking, while every image remains a recognisable pelican on a bicycle." src="https://static.simonwillison.net/static/2026/gemini-grid-updated.webp" /></p> <p>As I've done with <a href="https://simonwillison.net/tags/yonkers-rising/">several recent models</a>, I also fired the following prompt against Gemini 4 Neon on "extra" effort level in Google Antigravity:</p> <blockquote> <p><code>Make a three js animation where yonkers stands up as a big mech (cool stand up motion) and stomps around manhattan and queens and Brooklyn, use openstreetmap mapping data</code></p> </blockquote> <p><a href="https://static.simonwillison.net/static/2026/gemini-4-neon-yonkers/

74

Show HN: Zpup – Zdog style 3D scenes in JSON, SVG from any angle

60

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 15 tương tác đã đo · Nguồn crawl

select1dev 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn

Hi. I made small project called Zpup. It takes small 3D scene written in JSON and gives back a flat SVG from any angle. There is no JavaScript in the file, so it works in img-tag or README. I needed 3D for small project at my company, and Zdog make big impression on me. But Zdog has not had a release for several years, so I wanted to make modern version. One thing works different. Zdog sorts each shape by one point. so small thing on big floor gets covered when you turn it. Zpup compares the shapes that overlap. You can see both in the README. I wrote it with Claude Code Fable 5.2. No canvas renderer, no text shape, and it is 0.2 version. Playground: https://rxolve.github.io/zpup Feedback is always welcome :)

76

Evidence-Based Credit Assignment for Search-Augmented Language Models

80

8 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 3 tương tác đã đo · Nguồn crawl

Wen Wang, Jindong Wang và 6 nguồn khác 1 bài viết · Hugging Face Papers, arXiv cs.AI
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo nói rằng reinforcement learning từ phần thưởng cuối cùng cho phép search-augmented language models xen kẽ suy luận và truy xuất mà không cần nhãn từng bước, nhưng giám sát theo kết quả gán credit giống nhau cho mọi lần tìm kiếm trong một trajectory, dù có truy xuất hữu ích hay không. Họ giới thiệu Evidence-based Credit Assignment (ECA) để bổ sung tín hiệu phụ (training-only) đo việc các tài liệu đã truy xuất cải thiện xác suất của câu trả lời tham chiếu. ECA dùng evidence-only prompt với chỉ câu hỏi và các tài liệu đã quan sát (đã loại trùng), để tách tiện ích của đoạn truy xuất khỏi biến thiên do câu chữ suy nghĩ/ truy vấn sinh ra.

Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved useful information. This limitation is especially severe when all sampled rollouts for a question fail, collapsing group-centered outcome advantages to zero even when trajectories gather markedly different evidence. We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference answer. Rather than scoring the full dialogue prefix, ECA queries a frozen snapshot of the current policy under an evidence-only prompt containing solely the question and the deduplicated documents observed so far, isolating the utility of retrieved passages from surface variations in generated thoughts or search queries. Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment. Across seven Search QA benchmarks, ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO. Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.

  • ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO.
  • ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO.
  • Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.
  • Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment.
78

Code World Model 2.0: Towards Infinite Controllable Video Generation

82

12 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 9 tương tác đã đo · Nguồn crawl

Ruoyu Wang, Hao Zhong và 10 nguồn khác 1 bài viết · Hugging Face Papers, X
Biên tập tiếng Việt
Chi tiết nguồn

Bài báo mô tả cách các “visual proxies” tách việc mô phỏng trạng thái thế giới khỏi sinh video hiện thực, cung cấp một giao diện điều khiển cho tạo clip ngoại tuyến và streaming tương tác thời gian thực. Họ nêu hai thách thức: các proxy thay đổi theo mức độ tương tác, và suy luận streaming cần chạy trong vài bước nhân quả mà không tích lũy trôi do lịch sử tự sinh.

Visual proxies decouple explicit world-state simulation from photorealistic video synthesis, offering a controllable interface for both offline clip creation and real-time interactive streaming. Yet a practical renderer must address two challenges. Upstream proxies vary from coarse layouts to fine articulated geometry depending on the interaction, and streaming inference must operate in a few causal steps without accumulating drift across self-generated history. We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language. Trained on an aligned approximately 200-hour multi-granularity corpus, Invoker-Render honors fine geometric constraints when supplied while synthesizing plausible local motion under coarse proxies, enabling runtime selection of input detail. To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing). ProForcing first trains a causal predictor and distills it into a four-step renderer using histories derived from training videos. Training then shifts to continuous self-generated rollouts. A pipelined serving stack supports efficient streaming inference. Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.

  • We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
  • We present Invoker-Render, pairing a bidirectional creation model with a causal four-step streaming model under a shared conditioning interface over structural proxies, an appearance reference, and language.
  • To bridge bidirectional creation and real-time streaming without compounding step compression and rollout drift, we introduce Progressive Forcing (ProForcing).
  • Experiments show versatile control across proxy families, granularities, and camera paths, consistent gains over recent streaming baselines, and stable 30-minute racing rollouts that preserve scene and subject appearance.
79

Pyrefly v1.5.0

59

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 11 tương tác đã đo · Nguồn crawl

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

Ask HN: Tips for transitioning from web development to embedded/firmware?

58

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 11 tương tác đã đo · Nguồn crawl

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

I started my career 15+ years ago doing native development (c, c++, etc), but the last decade I've been doing fullstack web applications. I'd like to transition closer to my roots with a job doing primarily c, c++ or rust. The natural place seems to be in embedded development or firmware work. How feasible is the transition this late in the game? Any advice?

61–80 / 176
Trang 4 / 9