Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

Show HN: Natel, a self-hosted contacts editor for CardDAV servers in 20MB of RAM

Hi HN, I decided to move away from Google Contacts and self-host my contacts two months ago. After installing a Radicale server, I was really missing a way to edit my contacts on the desktop. Nextcloud is overkilled for my needs, and InfCloud is the only other web contacts editor but it hasn't had a release in more than 10 years.So I built what was the missing piece in my setup : Natel, a lightweight self-hosted contacts editor for a CardDAV server. The goal is to edit your contacts on the web, be robust enough to not make you lose anything when there's an edit conflict with the server, and be super light in resources on the server. I came up with building a docker image of just a proxy caddy server and a go process that stores your credentials only in-memory, for a compressed image of less than 30MB and it uses less than 20MB of RAM when idle.Tested against four CardDAV servers : Nextcloud, Radicale, Baïkal and Xandikos. I already use it myself and it syncs with my server and DAVx5 back-and-forth, but I consider it still in beta and want to add more testing to prove compatibility for features I don't (yet ?) use. Note that any field that isn't displayed is never lost, it's just written back as-is.Demo: https://demo.natel.app/contacts Website: https://natel.appI wouldn't have done this side-project if I couldn't delegate writing the code to agents. We iterate on architectural decisions together, and once I'm satisfied with the direction, they write the result in a file (find it in docs/DECISIONS.md in the repo), then write the code to meet the expectations and independently review each other's iterations. I drive the project's direction and decisions, but I don't review the code myself. I keep an eye on the tests to know what's covered, and will read and review code when an agent draws my attention to it. The e2e tests were able to find a bug in SoGO, a CardDAV server : https://bugs.sogo.nu/view.php?id=6269 (and I didn't add that server in the compatilibity list yet because that bug breaks one the promises of the app, which is to be warned if we're trying to delete a contact that is modified elsewhere ; the server doesn't correctly enfore the If-Match instruction)As I don't have that many users yet, I welcome feedback on any part of the project but especially the parts that I have not yet tested like Contacts on a Mac ! Comments URL: https://news.ycombinator.com/item?id=50439845 Points: 1 # Comments: 0

Show HN: Show HN: Sowbot – Open-hardware agricultural robot 8months progress

8 Months ago I made this post https://news.ycombinator.com/item?id=47123894Since then we've done stuff, the software is much more mature, we've done some basic field testing on small dev platforms.We've moved from ESP32 for the microcontroller to a STM32.Volunteers have come, gone again, new ones arrived.We're getting ready for full scale field trials now.Been putting some videos of sim up on https://www.youtube.com/@rosmo-robot/videosPlease critique again, and come join us! Comments URL: https://news.ycombinator.com/item?id=50437978 Points: 1 # Comments: 1

Show HN: We Gave AI Coding Agents Production Memory

Hi HN, I’m building Codela to help coding agents learn from what happens after their code ships.I realized that my AI agent writes a change, the tests pass, and it gets deployed. Then in production a problem happens, I fix it, but what it did wrong and why never reaches the agent, so futures session usually make the same mistake.Codela checks every deploy against how your app actually behaves in production, learns from the ones that broke it, and teaches your agents so they don’t repeat the mistake.Would love any feedback on this, thanks! Comments URL: https://news.ycombinator.com/item?id=50428670 Points: 1 # Comments: 0

Single-shot and agentic retrieval with Amazon Bedrock Managed Knowledge Base

Amazon Bedrock Managed Knowledge Base now supports single-shot RAG and retrieval-only requests through AgenticRetrieveStream, alongside agentic retrieval. This post explains how the maxAgentIteration parameter matches retrieval effort to each request, using an illustrative internal banking policy assistant.

Speed Insights and Web Analytics now support custom environments

Data from custom environments in Speed Insights and Web Analytics is now correctly attributed to the respective custom environment, enabling separate tracking for staging, QA, or canary environments. This update allows users to view and query data via the dashboard, CLI, query builder, and aggregation API without additional configuration, available on Pro and Enterprise plans.

Startup Founders Are Using AI To File Patents. Here’s Where DIY Becomes A Liability.

AI can help startups reduce patent preparation costs, but DIY applications may overlook critical issues. In this guest commentary, attorneys Michael Drapkin and Nathan Mutter of AI-Native law firm Landfall IP, argue that combining AI with legal expertise can produce more efficient, commercially valuable patent protection that withstands investor scrutiny and is harder for competitors to circumvent.

Vercel Sandbox snapshot creation is now up to 10x faster

Vercel Sandbox has improved snapshot creation speed by up to 10x, with median time dropping to under 0.4 seconds from 4.4 seconds, and restore speed improving by 50% to 250ms at p50. The enhancements leverage the Vercel Hive Snapshot (VHS) format with more efficient data indexing, enabling parallel read and write operations and faster restoration of both base images and user data. Persistent sandboxes now automatically snapshot upon session end and resume from the latest snapshot by default, using the new format for all new snapshots while existing ones retain the previous format.

Video-DCI: How Far Are VLM Agents from Human Viewers in Direct Video Corpus Interaction?

arXiv:2611.09951v1 Announce Type: new Abstract: Humans answer complex visual questions by inspecting short moments, updating what they know, and redirecting attention toward missing evidence. Existing video benchmarks, however, often provide the relevant video, evaluate only final answers or isolated localization, or permit textual shortcuts, leaving multi-round visual evidence seeking underexplored. We introduce Video-DCI, a diagnostic benchmark and functionally matched human-agent protocol for Direct Video-Corpus Interaction. It comprises DCI-Loc for temporal evidence localization and DCI-QA for end-to-end discovery, retention, and composition of cross-video evidence. In DCI-QA, videos within each pool are topically related, yet every answer requires hidden temporal evidence from multiple videos. Given only the question and video pool, humans and agents iteratively inspect bounded local windows, retain supporting evidence, and answer with cited temporal spans. Human trajectories provide reference curves for evidence acquisition and use across rounds. Experiments reveal a consistent retrieval-to-grounding gap. On DCI-Loc, frontier VLMs often retrieve and expose the reference moment, yet convert far less of this exposure into precise final citations than the human reference. On DCI-QA, the loss begins earlier and compounds across videos. Ablation studies further confirm that iterative search outperforms one-shot retrieval. Multi-round search is therefore necessary but insufficient: current agents accumulate candidates and observations more readily than precise, jointly sufficient evidence.

Wake me up when AI can...

Article URL: https://stoppels.ch/2026/10/03/wake-me-up-when-ai-can.html Comments URL: https://news.ycombinator.com/item?id=50440657 Points: 26 # Comments: 7

Aligning, Fast and Slow: A Control-Theoretic Oversight Framework for Long-Horizon Trajectories and Maintained Deployments

arXiv:2611.08781v1 Announce Type: new Abstract: AI agents can pass checks on individual tasks while retaining memory or code changes that alter their later behavior. We introduce a control-theoretic framework that couples a fast loop controlling proposed actions with a slow loop reviewing persistent changes and reassessing configurations after model or tool updates. When measurement errors and changes between checks are bounded and controllers can enforce their decisions, we derive a deployment-level bound and a rule for dividing review effort. In simulation, dividing a fixed review budget between both loops reduces mean maximum departure from intended behavior roughly twelvefold compared with review confined to individual runs. In coding stress tests with authored memories and five matched seeds, combined controls reduce mean severity on a 0-3 scale from 0.325 without gates to 0.117, resolving 33 of 120 issues versus 35 without gates; in trading stress tests, combined controls reduce mean shortfall in low-emission purchases from 0.892 without gates to 0.107. The overall framework helps developers and auditors compare and enforce oversight designs, while the agent studies test component controls rather than the full deployment-level guarantee.