@PeerReviewi
iAccount based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
product @youdotcom creator of https://nitter.cf/t.co/0Rqz1Id86I building AI search & dev tools
Cleveland
Joined June 2015
- Tweets611
- Following693
- Followers702
- Likes364
Pinned Tweet
I've been having a blast building a lil' Mac utility and today I'm giving it away for free.
It's so simple: Paste with a special hotkey and get contextual replies to anything.
I call it Super Paste.
Here is how use it 🧵
Sparker retweeted
Which companies will have a #1 AI model by December 31?
Live answer now with Knowledge on @youdotcom.
One parameter. No connector list to maintain.
Try it here - you.com/platform/playground/…
Sparker retweeted
🌐 Building an AI agent that needs web intelligence?
@youdotcom brings semantic web search and real-time retrieval directly into your Haystack agents!
Add YoucomWebSearch to your agent (or your pipeline), configure your You.com API credentials, and your agent can search the live web mid-run, pulling in content, snippets, and metadata that provide enough ground for downstream tasks.
Think of an agent that researches a topic in real time instead of working off its index.
🐍 pip install youcom-haystack
🔗 haystack.deepset.ai/integrat…
Sparker retweeted
Jev is a huge power-up for research agents!
@edwardirby built a @youdotcom agent that monitors business risks, and compared Jev to an ordinary LLM judge.
• Same report quality
• But the LLM flip-flopped: 0.35 -> 0.68 -> 0.50 on the same threat
• the LLM missed 5 of 11 investigations. Jev missed none.
• Jev was 250x cheaper, 3-6x faster
Write-up 👇
How to build a reliable risk agent without a frontier model ($0.02/sweep):
• @youdotcom search
• @typesafeai Jev for typed judgments
• @QwenDevs for proposals & synthesis
• MCP for integration
Full architecture & cost breakdown below 👇
Sparker retweeted
How to build a reliable risk agent without a frontier model ($0.02/sweep):
• @youdotcom search
• @typesafeai Jev for typed judgments
• @QwenDevs for proposals & synthesis
• MCP for integration
Full architecture & cost breakdown below 👇
Sparker retweeted
Give your agents access to the live web.
With @youdotcom + @Haystack_AI, your agents can search, retrieve, and reason over fresh web data in real time.
One component. One API key. Fresh results mid-run.
🌐 Building an AI agent that needs web intelligence?
@youdotcom brings semantic web search and real-time retrieval directly into your Haystack agents!
Add YoucomWebSearch to your agent (or your pipeline), configure your You.com API credentials, and your agent can search the live web mid-run, pulling in content, snippets, and metadata that provide enough ground for downstream tasks.
Think of an agent that researches a topic in real time instead of working off its index.
🐍 pip install youcom-haystack
🔗 haystack.deepset.ai/integrat…
Sparker retweeted
Super collaboration hill climbing with @NVIDIAAI and @CoreWeave ! Great inference and great web search make a difference in RL
Web search is now part of how open-weight models get trained.
Partnering with with @NVIDIAAI and @CoreWeave, we've built a training stack that brings live web search into reinforcement learning, starting with @nvidia Nemotron 3.5 Lightning.
More to come as we open this up.
I hoarded my old electronics long enough for them to become relevant again:
terbium.app
Sparker retweeted
Almost every prompt requires web search. We are happy to announce our partnership with @youdotcom for AnythingLLM.
Every user now will get accurate, fresh, and rich web-search with ZDR right out of the box. Server, Desktop, & Mobile.
Read more: anythingllm.com/blog/you-com…
look mom, I'm famous
Proud to be on @Meta's partner lineup at Meta Connect 2026.
Our teams have been building together for months.
Sparker retweeted
hosting the first official NYC AI Assistant meetup this Thursday!
pumped to bring this community together
Link to RSVP: luma.com/hs7tckol
Need to provide more inspiration. There is an inspiration drought. We have endless tools, subsidized for a short time. No one knows what to do with it.
the operating system is the next and last layer of abstraction to disrupt. In a few months, you won’t have an interface to a model. The OS will be the harness.
you.com 🤝🏻 openrouter
very cool product using openrouter as a reranker - did you know we have this? yes we do!
3x fewer tokens. 84% accuracy on the Vertical RTK benchmark.
That’s what we got using Jev through @OpenRouter as a reranking layer for Knowledge, which we recently launched in the Web Search API.
Knowledge returns structured, real-time data from authoritative sources across domains like stocks, sports, and more. For many queries, that data answers the question directly, so much of the retrieved web context is unnecessary for the synthesis model.
Jev sits between retrieval and synthesis, selecting only the most relevant results to pass downstream.
Sparker retweeted
3x fewer tokens. 84% accuracy on the Vertical RTK benchmark.
That’s what we got using Jev through @OpenRouter as a reranking layer for Knowledge, which we recently launched in the Web Search API.
Knowledge returns structured, real-time data from authoritative sources across domains like stocks, sports, and more. For many queries, that data answers the question directly, so much of the retrieved web context is unnecessary for the synthesis model.
Jev sits between retrieval and synthesis, selecting only the most relevant results to pass downstream.
I asked my four old what she wants to be when she grows up and she said “Founding Member of Technical Staff”
This is web4
I’ve seen a couple of posts about this so wanted to demystify. Today, every Muse user gets a free computer in the cloud. It's a real computer, and we’ve designed the security architecture of the Muse Secure VM carefully so you and your Muse can do almost anything you could with a computer sitting under your desk while keeping you and the system safe from threats like prompt injection. We wrote about this at length in our security blog post – security.muse.ai. Activity in the “runtime cell”, which you share with your Muse is unfettered, but sensitive actions are all overseen by the Sentinel, which runs outside of that cell. Similarly, all sensitive secrets - like the passwords you enter into Muse’s secure credential storage - are also stored outside the runtime cell.
The runtime cell gets its own root filesystem (including a full Ubuntu linux image) separate from the host filesystem where your other more sensitive data lives. Because it is isolated from the sensitive stuff that runs on the same box, this means that we can, and do, offer users full visibility and control over the files in the runtime cell. Just as you can when you install Linux on your home computer, you can poke around and see all the files that make the system work - both debian system files and the binaries and data files that implement the parts of Muse which run in the runtime cell.
This was a very deliberate choice - your Muse Secure VM truly is your own computer in the cloud. You can install software in it, write and compile code, use the browser to surf the web: it is your own Linux box that you can operate as you choose with your Muse. Poking around in this computer doesn't give you any privileged access to Meta infrastructure, or to other people's data
If I may geek out a little here for a second… As a kid I loved to take things apart to see how they worked. As a teenager I got into computers and soon found myself drawn to C:\WINDOWS\SYSTEM and the system registry, later Slackware’s /dev/, /proc/ etc – I could see how the system was laid out and as I explored what DLL files and .so files actually did, I gradually became able to meld the computer to my own will.
We’re really proud to be able to put a real computer in millions of people’s hands with a similar level of transparency. We built a file explorer right into the Library tab of the UI. We want you to be able to see the markdown files Muse writes while it thinks about how to serve you better, and explore the internals of the system if you’d like to.
So, when you ask your Muse to show you its entire filesystem, and receive gigabytes of files you’re seeing the full contents of the runtime cell. It’s yours to explore and enjoy!
If you’re not a geek like me, or simply want to download the data that you personally have created directly with your Muse, we added a feature for that too in Settings > Data controls > Download your agent data.
Lovable hitting $600M ARR on nearly a billion monthly views is a good reminder that "vibe coding" isn't a toy category