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: 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

Show HN: Comemo – composite memory provider for Hermes Agent

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

Show HN: Open Logs – Self-hosted log management on your own Cloudflare account

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

Show HN: Semantic/Structural diffs powered by Jev

Bit of a promo/explainer video: https://x.com/plannotator/status/2122076678155604016?a=6kshg...https://plannotator.ai/sem-jiff/ Comments URL: https://news.ycombinator.com/item?id=50510982 Points: 1 # Comments: 0

Show HN: Shutters – Photos and More

My mom is a photographer and an artist. This year, she complained that she doesn't quite enjoy the existing options for storing, sharing, and organizing her work.After a few sessions, I think we got into the ballpark of what it should look like if we weren't Google or SmugMug: with a host of extra features (clutter detection, decent search, book and album writing, even calorie and activity tracking, and a few other conveniences)The original intention was to build an application that would serve our family. But I feel like it's growing into something bigger as people are joining in. If you want to try, here's an invite code (capped at 50 signups): YRASHK-7ZXA-S3K3-DM8V Comments URL: https://news.ycombinator.com/item?id=50510836 Points: 1 # Comments: 0

Show HN: Strata Architecture

I've long thought about how we're influenced by CPU architectures, and importantly, their ISAs.In a discussion at a meetup, I brought up a topic that interested me for a while: how would an ISA that exposes memory and cache interactions in a more explicit way (because if you think about it, memory is very much I/O), as opposed to being smart and predictive on its own?An obscure interest, of course. Nevertheless, I wanted to build a quick prototype after that.What ended up transpiring was a bit larger. A multicore architecture with tiered stores, capabilities, a JIT'd emulator, Verilog RTL with a simulator, a small microkernel OS, UI, JIT Forth, an assembler in its own assembly, a bootstrapping C99 compiler, a few games, a visual debugger, and a few other things.(This also shows just how far a directed LLM process can go in little time) Comments URL: https://news.ycombinator.com/item?id=50510744 Points: 2 # Comments: 0

Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation

arXiv:2611.17589v1 Announce Type: new Abstract: Small open-weight language models can run crowd decision-making (CDM) on an institution's own infrastructure, which keeps the checkpoint, the inference settings and the opinions under its control. Their judgements vary across repeated queries; whether repeating and aggregating them, often through the 2-tuple linguistic representation, settles the decision rather than the labels is untested. Five open-weight models of 8-36B total parameters on one consumer GPU and a hosted reference classify 474 TripAdvisor reviews of four London restaurants ten times each; three open-weight models repeat the protocol on 600 reviews of twelve Madrid restaurants. Continuous evaluations preserve resolution: snapping each review leaves 5 distinct values against 21-65, and snapping at every level at most two collective values. Sensitivity to the participants persists once run-to-run variability is reduced: in London, redrawing the reviewers keeps the winner on 47-81% of replicas against 86-100% for redrawing the runs. With simultaneous intervals over every pair of alternatives under crowd resampling, no system on either corpus names a single winner: in London every system keeps all four restaurants as candidates, and in Madrid the candidate sets hold five to eight of the twelve. Extra runs and output-level fusion stabilize the winner but do not remove that sensitivity, and the fusion does not beat its best member. The three larger open-weight models name the hosted reference's London winner and at least match its per-review correlation with the reviewers' stars, so small open-weight models can support local CDM, reported as candidate sets with margins rather than forced rankings.

Split-and-Scale Latent 3D Representations

Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this progress, current representations struggle to capture the fine details of complex objects, fundamentally limited by the capacity of their latents. However, scaling latent capacity at training time is computationally expensive and often infeasible under memory limits, and naively increasing the number of latents at inference fails to make effective use of the added capacity. In this paper, we address…

When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors

arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity intervention moves hard-drop from gains of +0.186 to +0.230 at perfect resolution to losses of -0.176 to -0.181 at the lowest tested reliability. Paired targeted interventions show that false-drop causes significantly greater degradation than false-keep, while a non-deleting baseline can still fail when incorrect labels steer generation. On a frozen 102/102 calibration/test split, a simple deployment-matched gate reaches 0.655 accuracy versus 0.641 for always hard-drop and 0.662 for test-informed oracle selection. Global-accuracy crossovers require gold labels and are model- and task-specific diagnostics, not deployment thresholds. Deletion should instead be treated as cost-sensitive: validate query-critical false-drop risk on matched data, or default to label-free retention when such validation is unavailable.

b12397

The update introduces a change to the template soft_max_f32_parallelize_cols_single_row to store column elements in registers when feasible, reducing global memory traffic from five passes to two, thereby improving performance on CUDA-enabled systems.

Show HN: A blog on how computers work from scratch (1)

I started learning and writing up this blog in my own words, combining multiple resources until I feel comfortable in my understanding and then writing them down on my own. No AI here (other than help during the learning). This is article 1 of the series.Started understanding the flow of things from wall outlet, I know I skipped the things around how sand turns into a chip, but it would have gotten very long, maybe a story for another time.Looking for some feedback. Comments URL: https://news.ycombinator.com/item?id=50503921 Points: 2 # Comments: 2

Show HN: a Rust implementation of the Reticulum mesh networking stack

This is a fork of original rust sdk from https://github.com/BeechatNetworkSystemsLtd/Reticulum-rs/ that I extended significantly to make it fully feature compatible with the reference implementation that is built in python. I wanted to expand the rust sdk to give me full toolbox and easy way to do bindings for different languages including for building mobile apps.it covers the full surface: pathfinding and announce propagation, links, requests, resource transfers(bzip2, same wire format), identity ratchets, tunnels, LXMF messaging with propagation sync, serial/KISS/AX.25, RNode (incl. BLE), IPv6 auto-peering and I2P interfaces, Kotlin and Swift bindings so mobile apps can embed the stack directly.CLI tools (rnstatus, rnpath, rnsh, rnx) are ported too.I've done some experiments with it liek creating a LoRa chat firmware for the M5Stack Cardputer and a full node/repeater for M5Stack Unit C6L to have a tiny reticulum node with full stackBefore anyone gives me shit - I've opened an upstream PR but given the size of the change I'dnt blame them for not wanting to deal with it. Comments URL: https://news.ycombinator.com/item?id=50506235 Points: 1 # Comments: 0

Show HN: Can a VPN be decentralised.. I think it's the best for homelabs

Can a VPN be decentralised... I was trying out tailscale for my homelab but I didn't really want a control plane. Tailscale, Headscale and others already do the Controlled VPN extremely well, and I've used them. but every one of them has a control plane that all the devices directly connect to. I wanted something where every device in the network can act as a self node, and it'll be a Mesh of devices interconnected. Further it also allowed me to keep internal names like nas.home.kith.internal, and exit nodes, relays... it's free and open source (AGPL), written in RustIt really felt useful to me so I just want to know what would make it further helpful? ... Some use cases or if there's a problem it could actually help with, I'd love to hear it and try my best.ps : I used a lot of Claude while building it, so I'm sure there are rough edges I haven't found... bad code, wrong docs, or maybe the wrong approach somewhere. Would love any feedback on it, or anything I should do differently :D Comments URL: https://news.ycombinator.com/item?id=50505492 Points: 4 # Comments: 0

Show HN: Paintpot – Kid-friendly MSPaint clone for Linux

Most of the alternatives diverged from the true fun of MSPaint that I had as a child. My children also seem to enjoy this. The closest existing project was "Drawing" on Linux, but I felt it couldn't decide if it was a vector or a raster editor, and this confused my kids, and made good fill pours difficult.Features added beyond original Paint: - Draw circles starting from the center. - OKLCH Palette - Visible pixel grid when zoomed in. - Builds on Linux and Windows. - Written in rust. Comments URL: https://news.ycombinator.com/item?id=50501354 Points: 1 # Comments: 0