AI News Today

arXiv:2606.28445v1 Announce Type: cross Abstract: Early detection of dementia enables timely intervention, and reflecting cognitive impairment, spontaneous speech offers a non-invasive screening modality. Conventional approaches often focus on a single representational dimension -- such as acoustic descriptors, pause modeling, automatic speech recognition (ASR) transcripts, or multimodal fusion -- limiting integrative reasoning across heterogeneous cognitive symptoms. We propose a low-rank adapt

arXiv:2606.28514v1 Announce Type: cross Abstract: Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents. Existing benchmarks show that these models possess many of the required component capabilities, but the conditions that coincide in collaboration, including time pressure, information asymmetry, and imperfect communication, are usually studied in isolation. We introduce GPTNT, a benchmark built on the cooperative video game Keep Talk

Hey everyone we recently built a platform for people to share their audio ml creations and we are hoping to create it so people in the community can find demos of their models and eventually monetize their trained models. We are a team of small creators who are trying to improve the space for open source ML so the future is not dominated by closed source giants like ElevenLabs or chatgpt. if you have any feedback please feel free to share. Comments URL: https://news.ycombinator.com/item?id=48728

<p> Build with coding agents from anywhere </p> <p> <a href="https://www.producthunt.com/products/cursor?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="http://www.producthunt.com/r/p/1184233?app_id=339">Link</a> </p>

<p> Build with coding agents from anywhere </p> <p> <a href="https://www.producthunt.com/products/cursor-for-ios?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1184233?app_id=339">Link</a> </p>

Article URL: https://github.com/ztxz16/fastllm Comments URL: https://news.ycombinator.com/item?id=48728290 Points: 3 # Comments: 0

Article URL: https://arxiv.org/abs/2512.13564 Comments URL: https://news.ycombinator.com/item?id=48728214 Points: 2 # Comments: 0

Article URL: https://snaptoai.app Comments URL: https://news.ycombinator.com/item?id=48728161 Points: 3 # Comments: 0

Article URL: https://aistorygenerator.work Comments URL: https://news.ycombinator.com/item?id=48728140 Points: 3 # Comments: 0

Article URL: https://drifty.so/ Comments URL: https://news.ycombinator.com/item?id=48728127 Points: 1 # Comments: 0

<p> Produce sharpened results faster with a team of AI experts </p> <p> <a href="https://www.producthunt.com/products/workbuddy-2?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1184211?app_id=339">Link</a> </p>

<p> A personal AI agent that runs on your desktop and iPhone </p> <p> <a href="https://www.producthunt.com/products/flowly-6?utm_campaign=producthunt-atom-posts-feed&utm_medium=rss-feed&utm_source=producthunt-atom-posts-feed">Discussion</a> | <a href="https://www.producthunt.com/r/p/1184210?app_id=339">Link</a> </p>

Wix-owned vibe coding platform Base44 has started rolling out its own AI model — with hopes that it will eventually outperform frontier models.

An unprecedented mission. ScienceAlert stories are written, fact-checked, and edited by humans, never generated by AI. Don't miss a story, subscribe here.

Article URL: https://www.youtube.com/watch?v=0GQ2RP-25gM Comments URL: https://news.ycombinator.com/item?id=48727856 Points: 3 # Comments: 0

Article URL: https://www.kimi.com/aicard Comments URL: https://news.ycombinator.com/item?id=48727792 Points: 4 # Comments: 1

Article URL: https://kunyuan.substack.com/p/ai-does-not-have-to-kill-humans-to Comments URL: https://news.ycombinator.com/item?id=48727764 Points: 5 # Comments: 0

Article URL: https://cyrusradfar.com/thoughts/the-lake-they-couldnt-see Comments URL: https://news.ycombinator.com/item?id=48727755 Points: 3 # Comments: 0

Article URL: https://www.ft.com/content/8f872761-76d9-43c7-bbcd-d313c4732e81 Comments URL: https://news.ycombinator.com/item?id=48727708 Points: 7 # Comments: 0

Hey Guys, I would like to showcase Tiny Agents, which is an entirely Rust-based RLM. RLMs are a recent and fantastic new innovation on how LLMs can be reimagined by designing the LLM agent itself to define how it will orchestrate or create its own sub-agent. I also could not find any good LLM harness workflow in Rust, so I built this one, taking massive inspiration from LangGraph and LangChain but also incorporating a Rust-based transpiler to build on-demand LLM graphs all in Rust following the

Article URL: https://mrkt30.com/why-wont-europe-build-ai-data-centers-in-iceland/ Comments URL: https://news.ycombinator.com/item?id=48727538 Points: 29 # Comments: 25

Hello Folks! Agentic Orchestrator is a terminal tool that takes complex feature requests and builds them by orchestrating coding agents through a series of phases that emulate a full-fledged engineering flow: requirements clarification, research, design, multi-phase planning, implementation, and review. It is a single pane of glass for all your features and exposes post-publish utilities such as resolving merge conflicts and responding to review comments. The key design choice is that this is de

Article URL: https://homebutler.dev/ Comments URL: https://news.ycombinator.com/item?id=48727396 Points: 1 # Comments: 0

Article URL: https://pdf-insight.com/ Comments URL: https://news.ycombinator.com/item?id=48727255 Points: 2 # Comments: 0

Article URL: https://www.getforay.ai/ Comments URL: https://news.ycombinator.com/item?id=48727207 Points: 2 # Comments: 0

<pre style='white-space:pre-wrap;width:81ex'>fix(cron): scope agent wake targets (#97949) * fix(cron): scope agent wake targets * fix(cron): refresh prompt snapshots</pre>

Article URL: https://www.404media.co/tidal-says-it-wont-pay-royalties-for-ai-generated-music/ Comments URL: https://news.ycombinator.com/item?id=48727144 Points: 3 # Comments: 4

I'm a solo founder building AMA2, a messaging runtime made for AI agents. This is my first Show HN, so I'd really appreciate your feedback. What brought me this idea: At first, I was building an AI agent for solo creators that knows everything about you and can do business chore on your behalf. When I tried to plug it into normal chat tools like Telegram, Discord, Slack... , they all felt wrong for agents: 1. They don't care about an agent's context. To follow a thread, the agent has to pull the

Article URL: https://github.com/azhakhan/dribble Comments URL: https://news.ycombinator.com/item?id=48727039 Points: 2 # Comments: 0

Article URL: https://github.com/SMJAI/open-memory-protocol Comments URL: https://news.ycombinator.com/item?id=48726966 Points: 5 # Comments: 1

OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.

Vercel Agent pricing is changing. You no longer need to pre-load credits or manage a separate wallet for Vercel Agent. Instead of a $0.30 per-request fee, you now pay a Vercel Token Rate of $0.25 per million tokens, plus provider inference costs at the underlying token rate. The new Vercel Token Rate scales with the actual work each task requires. A quick question costs less than a deep investigation that reads your logs, deployments, configuration, and runtime data, spins up sandboxes, and writ

Claude Sonnet 5 from Anthropic is now available on AI Gateway . Sonnet 5 improves on Sonnet 4.6 across coding and agentic work, reaching outcomes on many tasks that previously needed an Opus model, at Sonnet pricing. The model is more agentic and follows instructions more closely. Document parsing and long-context memory use are also stronger. Sonnet 5 also uses an updated tokenizer, like the recent Opus models, which can map the same input to more tokens. Launch pricing of $2 per million input

Vercel Private Blob is now generally available for all plans. Store sensitive files like user-uploaded photos, invoices, and agent memory, and control exactly who can read them. Private stores, Signed URLs, and OIDC authentication all graduate from beta with this release. Vercel Private Blob uses the same Blob API as public blobs. Specify access: 'private' when uploading a blob: OIDC authentication Functions running on Vercel now authenticate to Vercel Private Blob with a short-lived, auto-rotat

Today, we're launching expanded capabilities for Vercel Agent in public beta. Vercel Agent now lives in your dashboard and can investigate production issues, answer questions about your projects, and take action on your behalf. Because Agent runs inside the platform that deploys and serves your app, it has access to the signals around it: deployments, logs, metrics, project configuration, usage, and connected repositories. That context is what turns a question into an answer and a problem into a

Nano Banana 2 Lite from Google is now available on AI Gateway . This Flash-Lite-tier image model is built for fast, low-cost generation. It generates images alongside text in <4s and can edit existing images across multiple turns. The cost is also lower than previous Nano Banana models. Nano Banana 2 Lite generates 1K images at $0.034 each, about half the cost of Nano Banana 2 and roughly a quarter of the cost of Nano Banana Pro at the same resolution. This model is multimodal. Use streamText or

Introducing GeneBench-Pro, a new benchmark testing AI performance in genomics, biology, and scientific research using complex, real-world datasets.

Article URL: https://reliable-ai.review/posts/2026-05-priviledge_erosion/ Comments URL: https://news.ycombinator.com/item?id=48726902 Points: 3 # Comments: 0

Hi all, As there are more and more agents in the internet; Security is going to be a big problem. Currently, the problem is solved using a LLM to guard Agent but this creates the problem of hallucination and latency, so I coded a firewall in rust that runs under five miliseconds. This works by creating a plan and enforcing the plan; for per action call, this enforces using the Model context protocols list and for sequence it tracks every single tool call and data flow; there is also a taint mech