mediablur
33 posts

mediablur
@mediablur
Exploring the intersection of AI & media tech | Focus on audio/video innovation | Passionate about empowering creative expression through emerging technologies
Aurora, Colorado Katılım Nisan 2009
149 Takip Edilen25 Takipçiler

@testingcatalog No voice mode yet, but at least we’ve got something 👏
English

@testingcatalog Heard any updates on when the Android app will be released?
English

@kevinweil It would be great if you added API support for MCP to OpenAI models 🙏🏻
English

💥 Today we announced a bunch of new tools to help developers build reliable + useful agents.
* Three new tools: RAG/file search, web search, and operator/computer use
* All packaged together in a simple, powerful new primitive we call the Responses API
* Plus, we upgraded Swarm to the (open source) Agents SDK to make it easy to build, orchestrate, and monitor systems of agents
2025 is the year of the agent, with multimodal reasoning models making multi-stage agentic workflows real, and AI beginning to do real world tasks for you. We've got a lot more where this came from!
What agentic tools should we build next?
English

@AILeaksAndNews I'm hoping we get MCP, but of course that's Anthropic's idea so maybe not ....
English

Here is the link to today’s OpenAI live streaming titled New tools for building agents with the API
It will showcase API platform changes that make it faster and easier for developers to build agents
What types of agents would you like to see moving forward?
Tibor Blaho@btibor91
OpenAI livestream "New tools for building agents with the API" "We’re evolving the API platform to make it faster and easier for developers to build agents. Join Kevin Weil, Nikunj Handa, Steve Coffey, and Ilan Bigio at 10 AM PT today." youtube.com/watch?v=hciNKc…
English
mediablur retweetledi

@altryne Just a heads-up that Haize Labs is spelled incorrectly in the podcast notes for today's episode: "Verdict, a new open-source framework from Hayes Labs". I finally found the right company but thought I'd mention it in case it's something that can be fixed for others.
English

These are the only models available on the current Android app with a Pro account:
* Default (Optimized for fast search by Perplexity)
* Claude 3.5 Sonnet (Most advanced model by Anthropic)
* Sonar (Advanced model trained by Perplexity)
* GPT-4o (Latest advanced model by OpenAI)
* Grok-2 (Latest model from xAI)
English

@altryne This is disappointing: o3 mini has a training cutoff date of September 2021? I tried to get it to list the discography of the group "The Armed" since the discography is not straightforward, but it could only come up with 2 albums and had the wrong title for both and the wrong date for one. Deepseek R1 did MUCH better.


English

@altryne @AITinkerers I missed hearing about this somehow (and I listen to ThursdAI every week). Is there a way to track when this event is in Denver/Colorado?
English

Kicking off our first @AITinkerers Denver meetup of the year!
So many new faces, we may need to start waitlisting soon!


English














