@𝚕𝚊𝚗𝚐𝚌𝚑𝚊𝚒𝚗/𝚖𝚌𝚙-𝚊𝚍𝚊𝚙𝚝𝚎𝚛𝚜 2.0 is out! 🧵
Using MCP with your TypeScript agents up to MCP servers just got a lot simpler: support for the latest stateless version of MCP, tools that can check in with your users when they need something, much easier auth integrations, and a ton of QoL updates.
Here's what's new 👇
We are introducing Clef and Clef-flash, open-source decision models hosted on Workers AI for high-speed classification and agentic workflows. https://t.co/eilE3tV0F2 #BirthdayWeek
Higgsfield × GPT-6.1 Sol for ads is insane.
Run your paid ads from ChatGPT:
→ Set up and launch ads in your account
→ Research competitors for proven ad angles
→ Turn one product photo into a batch of ads
We raised a $4.5M seed to let agents text people.
Since April: 50K+ developers, 450K monthly npm downloads and 10x revenue.
Bring your agent to iMessage, WhatsApp and more → https://t.co/RVaQzPBimT
Safety refusal reporting in the Artificial Analysis Coding Agent Index now shows when refusals occur and which models are used as fallbacks
We've added two ways to explore the results:
➤ Refusal timing: see whether a refusal occurred from the task prompt alone or later in the task, after the agent had already started working
➤ Fallback model: see which model the agent switched to after a refusal, alongside attempts that were blocked
Claude Code with Sonnet 5.5 (max) currently ranks first in the Index. Its safety refusal rate is 4.5%, roughly half the 8.9% recorded for Claude Code with Opus 5.5 (max).
Around 94% of Sonnet 5.5's refusals occurred after the first turn. Following a refusal, the agent almost always switched to Opus 4.8.
Observed fallback patterns vary across model and agent configurations. With Fable 5.1, Claude Code fell back predominantly to Opus 4.8, while Opus 5 accounted for a much larger share of Devin Fusion's fallbacks in the Index.
Both views are available for the overall Index and each benchmark. Safety and fallback behavior is provider-configured and may change over time; these rates reflect behavior recorded at the time of benchmarking.
Introducing fal Recast, an easy way to change any character in one click.
Upload an existing video + a reference photo of your new character. fal Recast changes who’s on screen while preserving the original motion, camera movements, cuts, and audio. Create character variations, adapt campaigns for different audiences, all without another shoot.
Powered by H3 Max, the #1 model for overall quality, prompt understanding, and aesthetics against leading video models.
The Laya decision model is free on AI Gateway via @BoundlessHQ through Oct 31.
Use it to route agent work, triage support, and check guardrails.
𝚌𝚘𝚗𝚟𝚊𝚒𝚒𝚗𝚗𝚘𝚟𝚊𝚝𝚒𝚘𝚗𝚜/𝚕𝚊𝚢𝚊
https://t.co/UvUqycWcjs
Grok Imagine Video 1.5 Lite is now available on fal
The lightweight model in the Grok Imagine video family
Text-to-video and image-to-video with native audio, 1 to 15 seconds
480p, 720p and 1080p output across 7 aspect ratios, from 16:9 to 9:16
Your optimization tools diagnose problems but abandon you at the point of action.
AWS Well-Architected Agent delivers automation-ready fixes with the findings — all prioritized by your business goals.
From insight to action in minutes.
Everyone has been obsessed by Jev and what it can do, and they should be! Fast typed decisions >> slow text generation. It's a complete game changer. But how do you do that with all the data you have?
We just dropped 𝚊𝚒_𝚍𝚎𝚌𝚒𝚍𝚎(), which runs decision models natively on all your data in @databricks . Now you can run system one decisions on all your big data, see screenshot.
https://t.co/1kvMaxxFEt
What can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposureWhat can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposureWhat can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposureWhat can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposureWhat can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposureWhat can the Salesforce Winter ’27 Release do for your business?
Optimize agents. Control AI spend. Scale complex transactions. Reduce fraud exposure.
Two of the largest tasks in Cline the last 30 days:
- 9B tokens on Claude Opus 5: ~$8,500
- 9B tokens on DeepSeek V4 Pro: ~$300
That's about 30x cheaper for the same token count.
You don't need to spend thousands or wait on limit resets to get large-horizon work done anymore.
NEW: Anthropic investor day invites have gone out for October 14th at HQ in San Francisco, putting the company on track for an IPO in November https://t.co/cmjEblGrlc
We’re open sourcing a state of the art multimodal Decision Model, pplx-decider-27b, and are offering it in a new Decisions API at 4 cents per million input tokens and free output tokens. We intend to bring down the price even further over the coming days. Enjoy!
We are live-streaming Gemini 4 Argon playing Kerbal Space Program.
So far, Gemini 4 sits right between Claude Fable 5.1 and Gpt 6 Astra. Starting from a simple orbiter rocket, Gemini 4 Argon has landed and returned from the Mun (Moon), Minmus, Duna (Mars), Ike, Gilly, and Dres.
YUI is the first animated short film made with Comfy Agent.
We are happy to partner with @8co28 in this experiment. She made the full 4:20 film in 3 focused days of work. And we shaped the character together. YUI is the last three letters of ComfyUI.
The behind-the-scenes video, also generated with Comfy Agent, was made to echo the theme "The story does not end".
Comfy Agent handled shot regeneration, side-by-side model comparisons, and character consistency checks. That used to be weeks of manual testing and generation.
When you are the main character, what will you do if your story ends in 3 minutes?
Seedream 5.0 Flash from @ByteDanceSeed_ is now live on OpenRouter
The fast, cost-efficient tier of Seedream 5.0, built for high-volume generation and interactive editing at low latency
https://t.co/LG2HRmQbPs
Speech is now in Beta. Try the first model ever that creates spoken audio with matching background music. Update your app for the latest.
Read more here:
https://t.co/c9IA9imXRX
GPT-6.1 Sol is insane at browser tasks 🔥
> higher score than Astra
> 7.8x lower estimated cost
> highest score we’ve measured on Browser Use Bench 2.1
Why so cheap? 95% of its prompt tokens were cached and cached-token rate is 10x cheaper than Astra.
Opus 5.5 and Grok 4.7 also scored lower AND cost more.