News and site search
Explore related news, tools, models, guides, topics, workflows and prompts.
News stories 233
“AI Code Guide”
Show HN: Stromboli Open-source AI SRE agent focused on fast incident mitigation
Article URL: https://github.com/openstatusHQ/stromboli Comments URL: https://news.ycombinator.com/item?id=50523348 Points: 1 # Comments: 0
Show HN: Sutra-OS – A self-hosted ontology platform
Article URL: https://github.com/0nelight/sutra-os Comments URL: https://news.ycombinator.com/item?id=50525052 Points: 9 # Comments: 0
Show HN: Triton-ng – Write Nvidia Triton inference back ends in Rust
Article URL: https://github.com/rdcm/triton-ng Comments URL: https://news.ycombinator.com/item?id=50532862 Points: 1 # Comments: 0
Show HN: XDM – a FOSS IDM alternative since 2013 revamped and torrent support
This is the developer of XDMIn a time of bunch of vibe coded download managers XDM one of the oldest open source downloader that is been serving as IDM alternative from 2013. Apart from a modern beutiful UI XDM now comes with torrent support powered by Libtorrent (the engine behind famous qBittorrent) and a new yt-dlp wrapper on top of XDM's built in browser extension based video grabber.New features: - Torrent and magnet link support - Additional option for video download based on yt-dlp - Lightweight but modern UI. XDM still runs under 50mb of RAM - Brand new social media reels and profile downloaderCore features: - Dynamic segmentation based battle tested multi threaded download engine - Takes over downloads from browser and detects video playing in the browser - Runs on Windows, Linux ( with native wayland support ) and macOS. - Usual features: Pause/resume/refresh expired links, queue, scheduler, speed limit, custom actions after completion, proxy, authentication and many more. - Android version soonPlease visit GitHub repo for more info: https://github.com/subhra74/xdm Comments URL: https://news.ycombinator.com/item?id=50521479 Points: 2 # Comments: 0
Agents are users, so your software needs evals
Agents interact with software through a funnel similar to humans: Discovery, Selection, Access, and Success. To measure whether agents complete user tasks correctly, end-to-end (E2E) evaluations are essential. These tests run multiple trials, score outcomes, and help identify failures across steps like searching cafes, checking budgets, and placing orders. Using frameworks like Harbor, teams can define tasks with specific instructions, environments, verifiers, and known-good solutions. Metrics such as success rate, Pass@k, and Pass^k reveal how reliably agents perform, while trace analysis uncovers root causes of failure. The process includes setting a goal based on observability, customer feedback, or roadmap needs; defining measurable metrics; designing task sets covering common and edge cases; running evaluations at scale using tools like Vercel Sandbox and AI Gateway; and analyzing traces to iterate improvements. Automated trace analysis enables scaling, and repeated evaluation supports continuous improvement, regression detection, and product optimization.
LLM-Guided Cluster Lifecycle Management: Deciding When and How to Evolve Behavioral Clusters
arXiv:2611.17616v1 Announce Type: new Abstract: Behavioral clusters learned over user or item interactions drift as behavior evolves: some fragment into sub-behaviors, some converge, some disappear, and new patterns emerge. Two paradigms dominate the maintenance of evolving clusterings. Threshold triggers fire a pre-specified action when a hardcoded statistic crosses a cutoff; refit-and-track (MONIC-style) re-clusters every window and infers transitions from how the new clusters align with the previous window's. Both hardwire the decision into a threshold or a re-clustering rule. We study an alternative in which a large language model (LLM) makes the lifecycle decision in place. Given a threshold-free, whole-population view of the current cluster set (statistical health, labels, member texts, residual mass), the LLM decides per cluster whether and how to act (split, merge, retire, create, or no-action) without re-clustering. Because the useful signal channel depends on how informative the labels are, we fix a richness-conditioned policy in advance: statistics when label distinctiveness is low, fused statistics+semantics when it is high. On three public datasets spanning label richness (YooChoose 0.17, MOOC 0.50, News-Category 0.70), the policy-selected LLM mode obtains the highest F1 on all three, with far fewer interventions and stronger restraint than tuned threshold heuristics and a MONIC steelman (paired Wilcoxon p <= 0.003, bootstrap 95% CIs excluding zero). The gain is concentrated more in precision than recall. The useful modality shifts from statistics to semantics/fusion as richness rises. Semantics hurt on YooChoose, fusion is roughly neutral on MOOC, and the semantic channel is required on News. One base prompt template and one fixed policy serve all three datasets, whereas the tuned baseline collapses when moved between them. We treat this shift as a practitioner diagnostic observed on three datasets, not a validated law.
Qwen4-Max now available on AI Gateway
Qwen4-Max, the first model in Alibaba's Qwen4 series, is now available on AI Gateway. It features a 1M-token context window, native vision capabilities, and excels in coding, professional tasks, and long-running agent workflows. The model can generate and test 3D scenes in Blender and games in Unity, Unreal Engine, and Godot, while also handling complex document analysis for finance, legal, and healthcare use cases. It produces cited reports, spreadsheets, and slide decks, and supports iterative improvements via a Live Delivery plugin. Compared to previous models, it uses fewer tokens, writes more secure code, and integrates with tools like Claude Code, Codex, and Cursor through Vercel CLI setup. AI Gateway offers unified API access, cost tracking, Zero Data Retention, budget controls, and no markup pricing, including for BYOK requests.
Seedance 2.5 Flash now available on AI Gateway
Seedance 2.5 Flash, a faster and lower-cost variant of Seedance 2.5, is now accessible via AI Gateway. It delivers output comparable to the standard model in human realism, reference-based editing, and prompt adherence. Users can generate videos with synchronized audio from text prompts or references, supporting clips between 4 to 30 seconds at up to 720p and 24 fps in various aspect ratios. The model supports editing or extending existing videos and using images to define start and end frames. Integration is available through AI SDK 7 with example code for text-to-video generation and reference-guided creation using image and video URLs.
Show HN: A Postgres read-replica, but 10-50x faster for analytical queries
Article URL: https://github.com/embeddable-hq/mason-data Comments URL: https://news.ycombinator.com/item?id=50515362 Points: 3 # Comments: 0
Show HN: atl, a Rust CLI for Jira, Confluence and Bitbucket with ~15ms overhead
Hello HN,I built `atl`, a Rust CLI for Jira, Confluence, Bitbucket, Jira Service Management, Trello and Atlassian Admin. The same commands work on Cloud and Data Center (on-prem).It's built for both people and AI agents: an --agent mode that outputs JSON and never prompts, a built-in MCP server with 136 tools, and a read-only login so an agent can't change anything. Confluence pages can be edited as Markdown and kept in git.It has SDK support as well for Python, TypeScript/JS, and WASM.Any feedback and contributions are welcome! Comments URL: https://news.ycombinator.com/item?id=50509662 Points: 1 # Comments: 0