Find insight on Equifax, M&G, Sabre Insurance Group, National Australia Bank and more in the latest Market Talks covering Financial Services.

© carlo allegri/Reuters

Six-time Grand Slam champion Iga Swiatek ends her 2026 season after failing to qualify for the WTA Finals for the first time since 2019.

England begin their wandering winter with a sloppy loss to Pakistan in the one-day tri-series in Rawalpindi.

Staying quiet is riskier than speaking up, Ukrainian officials say, as President Trump goes farther than ever in prioritizing Russia’s interests.

© Ludovic Marin/Agence France-Presse — Getty Images

Article URL: https://mistral.ai/news/voxtral-3/

Comments URL: https://news.ycombinator.com/item?id=50168396

Points: 11

# Comments: 0

Arturia is adding to its Freak line of proudly weird digital synths with the MiniFreak 49. Under the hood, it's almost identical to the current MiniFreak, but it adds a number of more professional features and some interface improvements.

The most noticeable change is that, rather than the MiniFreak's 37 minikeys or the MicroFreak's 25 "key" touchplate, the MiniFreak 49 has (as you may have guessed) 49 full-sized, semi-weighted keys. Though it's somewhat disappointing that they feature only mono aftertouch instead of polyphonic aftertouch. It also trades the touchstrips of the other Freak instruments for proper aluminum pitch and mod wheel …

Read the full story at The Verge.

Article URL: https://lukaswerner.com/post/2026-10-20@bottom-up-vga

Comments URL: https://news.ycombinator.com/item?id=50168376

Points: 7

# Comments: 0

Plus, Musk’s donation pledge, and consumers are still wary of giving agents their credit cards.

© Jason Henry for WSJ

Mark Allen says that retiring from snooker is "something I have been contemplating for a while" following his 4-2 loss to Jordan Brown in the Northern Ireland Open.

It's a time of apocalyptic worldviews in Silicon Valley. The latest AI doom cycle is driven by effective altruism, a philosophy that has lurked around the fringes for years but recently burst into the mainstream because its adherents are embedded across the AI industry, from Anthropic to newly appointed AI safety watchdog METR. EA is a utilitarian approach to charity premised on doing the most good for the most people over the longest time, and EA advocates see halting an AI-induced doomsday as critical to saving as many humans as possible.

But EA has an important and equally apocalyptic rival in the crosscutting cosmologies of the tech tit …

Read the full story at The Verge.

The sixth report from Covid inquiry criticises the lack of PPE and the way patients were discharged from hospital.

Article URL: https://www.nber.org/papers/w35706

Comments URL: https://news.ycombinator.com/item?id=50167732

Points: 28

# Comments: 29

Once again, the president’s ability to wage a trade war without Congress will come before a court that has repeatedly ruled against him.

© Doug Mills/The New York Times

She said in a Tuesday release of her Messy podcast that she was not happy about the new information and her symptoms have only "gotten worse".

The BBC announced it will close its BBC Three, BBC Scotland and Radio 4 Extra broadcast channels.

I built a quiz game around TypeSafe's new Jev model, which has vision capabilities. Jev looks at a picture and a question and picks an answer (or taps a place) in about a quarter of a second.

I've always loved quiz games and thought this would be a fun way to see what it can do and how fast it is. I made the cards from scratch, and Jev gets exactly the picture you see. More cards will come over time.

Play against Jev on your own (there's a leaderboard for each mode), or start a live match and challenge your friends, with Jev as one more player.

The code is open source, so feel free to build your own game or make more cards that I can publish.

Play: https://jevcards.com Code: https://github.com/Jose-Sabater/jevcards (the newest cards stay private for a while)

Disclaimer: I ran Jev through both TypeSafe and Opper, and made the cards through Opper's vision models and Claude Code. I work at Opper, but jevcards is open source and free to play.

---

Comments URL: https://news.ycombinator.com/item?id=50167617

Points: 21

# Comments: 7

Article URL: https://github.com/AbdullahAlhariri/penmentor

Comments URL: https://news.ycombinator.com/item?id=50167604

Points: 12

# Comments: 1

Dougherty upset of Cairo earns Trojans AJC Varsity Team of the Week

Hey HN, this is Andy from Respan (https://www.respan.ai). We are building an open-source Rust AI gateway. It is a decoupled gateway, so everything is a plugin, including different providers, protocols (MCP, voice), modalities (images, videos), and gateway features (fallbacks, PII redaction, smart routing).

Instead of packaging tons of providers and features into one gateway, Respan provides a small core and public interfaces that teams can use to assemble the AI infrastructure their application needs. That way, users can build their own features as additional plugins without having to change the gateway's core.

Here’s a video demo: https://www.youtube.com/watch?v=pVv2ibXiTXM

There are countless LLM gateways and most of them solve a common problem: calling different providers from a single endpoint. However, adding new features can become prohibitively difficult. So developers can end up building another gateway to solve a specific problem.

We've been building our gateway based on LiteLLM since 2024, and now it's providing services for thousands of orgs. Each org needs different API key settings, routes, and limits. To support that, we kept wrapping LiteLLM, adding more features to it, and at one stage, our wrapper code exceeded 100,000 lines.

This January, a routine LiteLLM upgrade caused intermittent connection errors, and we had to roll back. We still haven't figured out the cause, but since then, we no longer upgrade LiteLLM directly and instead manually backport upstream fixes. These experiences made us realize that continuing to patch LiteLLM is not a sustainable long-term solution, and we had to redesign the gateway ourselves.

While redesigning our gateway, we wanted to make it easier to add features without breaking existing ones. Inspired by Nginx, we think an AI gateway should have a really small core, only responsible for dispatching events.

We believe that everything should be a plugin in our gateway, including providers (OpenAI, Anthropic, Gemini), protocols (chat, realtime voice, MCP), modalities (images, videos), and gateway features for reliability and security (smart routing, fallbacks, and PII redaction through example plugins). Beyond that, we want developers to be able to easily extend the gateway's capabilities by adding their own plugins, without touching the core. Adding a provider, even your own, is dead simple, because quirks are plugins too and there’s nothing magical about them. A provider is a short file, Mistral’s is 22 lines, and each quirk, like Groq putting token usage in its own field, gets its own test.

Respan Gateway does more than let you call Claude or Gemini models from the OpenAI SDK. It handles tools, images, and reasoning protocols automatically: an application based on the OpenAI Realtime API can also use Gemini Live through the gateway, though not every feature translates. A simple chat app can use MCP tools configured in the gateway, without implementing MCP itself.

We also parse requests into a shared structure. When the client and provider use the same API, we preserve provider-specific fields in their native format, even if our shared structure doesn't have a field for them. That way, the gateway can write them back instead of dropping them.

Here’s how it works:

An adapter hands each HTTP or WebSocket connection to the first client format that recognizes it. The format exposes the request as a two-way stream of typed input and output events. The core runs plugins in registration order, allowing them to choose a provider, filter or wrap either stream, make additional calls, return a response, or refuse the request. A provider format then opens the upstream connection.

If the client and provider use the same format and no plugin changes the payload, the original bytes and protocol-specific fields can pass through unchanged. When formats differ, they translate through shared types for messages, tool calls, results, streams, and usage. This stream model can represent both one-shot HTTP requests and long-lived bidirectional sessions.

The gateway is open source at https://github.com/respanai/respan-gateway under the MIT or Apache-2.0 license. You don't need to use Respan's hosted platform and can run it directly on your local machine. Build it from source, add your provider keys, and swap the base URL in a supported client. You can keep using the API your client already speaks. It's still pre-alpha.

We make money from our hosted platform (https://www.respan.ai/pricing), which runs the gateway for you with native observability and evals, along with unified billing.

If you’re building routing, tools, filtering, observability, or security for agents, we'd love to see it as a plugin. PLUGINS.md in the repo explains how to write one and links to the plugins we’ve created so far. Turning that into an ecosystem is basically our roadmap, and we welcome you to contribute your own plugins. We'd love to answer any questions and hear your feedback!

https://github.com/respanai/respan-gateway

---

Comments URL: https://news.ycombinator.com/item?id=50167583

Points: 14

# Comments: 8

Article URL: https://www.red5.net/blog/how-to-link-real-time-live-streaming-to-video-on-demand/

Comments URL: https://news.ycombinator.com/item?id=50167560

Points: 5

# Comments: 1