Show HN: Tom – meeting recording and feedback specs, all locally on Mac
Article URL: https://github.com/automatics-dev/mac-tom Comments URL: https://news.ycombinator.com/item?id=50531364 Points: 2 # Comments: 0
Search headlines, summaries and articles to connect the dots.
Article URL: https://github.com/automatics-dev/mac-tom Comments URL: https://news.ycombinator.com/item?id=50531364 Points: 2 # Comments: 0
Article URL: https://github.com/rdcm/triton-ng Comments URL: https://news.ycombinator.com/item?id=50532862 Points: 1 # Comments: 0
arXiv:2611.18956v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models add parameters without proportionally increasing per-token compute. However, training cost also depends on bytes moved, memory held, and kernels launched, and many of those costs follow total parameter size rather than active compute. On infrastructure built for dense models, this mismatch is costly: in early baselines, throughput fell as stored expert parameter size grew, even though the useful work per token stayed nearly fixed. To close this gap, we present a redesigned training stack in Olmo-core, built for efficient, scalable MoE training. We replace the Fully Sharded Data Parallel (FSDP) of earlier Olmo-core versions with an architecture built on Distributed Data Parallel (DDP), and add Expert Parallelism (EP), Pipeline Parallelism (PP), a distributed optimizer, and activation recompute. We propose NVSHMEM-based rowwise EP, which writes each token directly into its expert's buffer, avoiding dispatch and combine permutation overhead. We make EP fully synchronization-free by keeping routing metadata on the GPU and using device-scheduled grouped GEMMs. Closely integrated MXFP8 cuts compute, activation-memory, and transport costs, and topology-agnostic checkpoints let the parallel layout change between runs. On NVL8 B300 nodes, the stack supports training configurations from 12.9 billion to 1.2 trillion total parameters on up to 512 GPUs, reaching 858 useful-model TFLOP/s/GPU at 1.2 trillion with MXFP8 and per-layer recompute; an experimental capacity test with the optional DeepEP v2 backend reaches 2.38 trillion. We also explain each design choice and share findings for other training systems; for example, we identify a failure pattern we call Token Gerrymandering, in which the MoE router can learn to hack the load-balancing loss, and find that overlapping communication with computation can slow the overlapped kernels by more than it hides.
Multi-agent coordination is a distributed systems problem, not a model problem. This post gives a field-tested taxonomy of multi-agent design patterns and anti-patterns, a framework for deciding when multiple agents are warranted, and how to build cost-efficient, reliable systems on AWS.
Live Rewind and Siri Recap can transcribe missed moments and summarize your day—if you don’t mind a little social clumsiness.
arXiv:2611.20246v1 Announce Type: new Abstract: Multi-round diffusion image editing can reduce computation by reusing intermediate activations, but retaining these activations across editing rounds introduces substantial memory and bandwidth overheads. Compression can reduce these overheads, but efficient cache construction is challenging: compressing only after editing requires buffering over 100 GB of activations per request. Moreover, the compressed cache must support selective reuse, as future masked edits require only a subset of the cached activations. It also exposes a scheduling challenge, as cached edits are faster than initial generations, causing naive policies to severely delay either initial generations or editing requests. In this paper, we aim to address both challenges through compression-informed serving. We develop TileCache, a serving system for multi-round diffusion editing. It compresses reusable activations and incorporates a scheduler that balances both edits and initial generation requests. Compared with the state-of-the-art image editing baseline, TileCache sustains over 2x the request arrival rate at 90% SLO attainment. It completes edits 2.4-4.5x and initial generations 1.3-2.2x faster than the baseline, while preserving image quality.
arXiv:2611.18578v1 Announce Type: new Abstract: Long-video question answering is wasteful and lossy when a multimodal model must re-encode the same video for every query: context limits force sparse sampling or truncation, and no reusable representation remains for later questions. We present VidEngram, an agentic video QA system that builds a persistent hierarchical memory once at ingest and answers later questions from that memory. VidEngram captions video and audio jointly with Qwen2.5-Omni, consolidates segment memories into episode and entity layers, and uses a text-only agentic planner with specialized retrieval tools to produce grounded answers. The web interface makes this process inspectable: users can watch memory formation, inspect retrieval traces, verify cited evidence in the video player, and explore entity relationships. On the full OmniVideoBench, VidEngram with a GPT-5-mini planner outperforms a strong single-pass Qwen2.5-Omni baseline (37.0% vs. 32.3%), with gains concentrated on longer videos where single-pass coverage becomes sparse. Because perception is paid once, subsequent queries use low-cost text-only planning.
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.
Over two days at COEX, more than 2,000 attendees converged for AI Day Seoul, bringing together Korea’s industry leaders, startups and developer communities advancing physical AI and AI agents. At the plenary sessions, Deepu Talla, vice president of robotics and edge AI at NVIDIA, said Korea is “punching above its weight,” with Doosan Robotics, Hyundai […]
Define metrics once, give agents context, and keep pipelines fresh. See how healthcare teams build AI their care teams can trust.
As AI takes over entry-level knowledge work, guest authors Bob Morse of Strattam Capital and Michael Quoia of KSE Leadership argue that these workers should begin their careers managing AI agents, developing skills in delegation, oversight and judgment traditionally learned later.
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, 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.
The world of AI used to have people training models for solving substantial issues - like beat world's best go players or solving protein folding. Now that the AI got good, perhaps we forgot a bit how to do it. There is still cheap hardware around for tinkerers and people who want to continue good AI legacy. But the hardware may miss software. It is for those people that I started working on zyx long time ago - ML library in hopes of running on any hardware. One example of such hardware is tenstorrent. But the basics must be built first. And so today I'm showing you skamandros. A tiny, self-contained driver and compiler for tenstorrent cards (tested on p100a). PTX like input, mostly abstracted away hardware details (other than tiling), automatic optimizations and operation fusion. Hope you can use this software to write AI models that people can like. Comments URL: https://news.ycombinator.com/item?id=50509698 Points: 1 # Comments: 0
Article URL: https://github.com/embeddable-hq/mason-data Comments URL: https://news.ycombinator.com/item?id=50515362 Points: 3 # Comments: 0
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
There are many memory providers that can be used externally with Hermes Agent. However, like many other AI agents, Hermes only provides one slot for an external memory provider.Comemo takes that slot and acts as a composite provider. How? It fans out memory writes to multiple backends such as Mem0, Honcho, and Supermemory. On retrieval, it queries the enabled providers, merges their results, and removes duplicates before returning them to Hermes.I intend to add support for more memory providers and eventually extend Comemo to other open-source AI agents with similar limitations. Comments URL: https://news.ycombinator.com/item?id=50518538 Points: 1 # Comments: 0
Article URL: https://codecainehq.com/ Comments URL: https://news.ycombinator.com/item?id=50514822 Points: 5 # Comments: 0
Hi HN, I built Open Logs, a log manager that runs on your own Cloudflare account. I wanted a simple place to send logs from my own apps without running a server, so I built it on Workers and Basin.It's one Worker (Hono + React), D1 for app data, and logs go Pipelines → Iceberg in your own R2 bucket → Basin SQL. You get live tail, search, dashboards and alerts with webhooks. npm run setup creates everything in your account.Things I learned: every Basin SQL query is billed at a 10 MB minimum, which shaped most of the UI (cache everything, refresh only live data). Logs take 30 seconds to 3 minutes to become searchable, so the UI says so instead of pretending to be real time.Website: https://adithya188288.github.io/open-logs/ How I built it: https://codezenk.me/blog/open-logsFree and MIT licensed. Feedback welcome. Comments URL: https://news.ycombinator.com/item?id=50516451 Points: 1 # Comments: 0
Article URL: https://github.com/OpenTodoApp/OpenTodo Comments URL: https://news.ycombinator.com/item?id=50517352 Points: 2 # Comments: 0