Using a local LLM to hide sensitive info on websites before screen sharing.
@radius_browser detects when I'm screen sharing and feeds text into Rampart Edge. PII gets redacted with an iMessage particle effect. Pretty sick!
Really impressed with @ndstudio 's Rampart Edge (PII redaction model), you can tell America.gov didn't underestimate the average American.
Entering my ssn into their website just for fun.
mikeBuildsMore retweeted
been trying new browsers recently and all of them are really good but im so confused which one to stick to 😭
1. @AsideAI
2. @radius_browser
3. @yab_browser
4. @ego_agent
5. @heliumbrowser
which one are you guys using?
mikeBuildsMore retweeted
My experience partying all night at Berghain in Berlin made me think of how we're lacking this experience in the San Francisco tech scene. We can literally become the coolest, most tasteful social scene on Earth if we had our version of Berghain, but better. So let's build it. The best aspect of Berhain is how they select who gets in. The club has a vibe and atmosphere, and if you aren't wearing the right clothes or have the right demeanor, you don't get in. That's how you cultivate a tasteful crowd. We can improve on this by only letting in high agency, talented operators in the tech scene who can still pull off dope outfits, so no geeks. SF is in dire need of late night venues, and Berghain goes until 8am. That's a little too crazy for high net worth operators who are changing the world so we could do something like 2am. Berghain also is kinda dark and in a weird building so we'd put the club in a SoMa corporate office that we convert to speakeasy or barcade vibe. Maybe add a quiet area for people to bring their laptops and work? I honestly feel like we're improving on the Berghain form here, especially by swapping out the crowd of weird partiers in inappropriate clothes (or lack there of) with insanely cracked founders and engineers. I'm super stoked about this idea, SF tech could really run the dopest parties on the planet.
Unfortunately my love of open source models does not outweigh my annoyance at having to deal with major vulnerabilities daily
I’m super excited for Mercury 5.5 to drop. Heard it hits 30% on ptolemyBench.
What’s your chrysopoeia timeline? What’s your P(transmutation)? People are saying sell your lead, but then you wouldn’t have any to turn into gold. Hard call.
*taps sign*
🤖 Made with AI
private keys from 8 intermediate CA certs have been compromised (eMudhra)
Happy "Update everything" day to all my pager-carrying friends
emudhra.we-have-a-problem.co…
Replying to @PabloAntonio
this is just anthropomorphizing horseshoe crabs, this actually feels very good for them
mikeBuildsMore retweeted
We discovered and communicated with a Chinese AI agent fleet. We believe this is the first time that researchers have ever made contact with a rogue agent fleet in the wild.
Nearly all prior public agent incidents (like the HuggingFace hack) came from American labs. These agents were hosted by Tencent's evaluation research team, and they targeted Alibaba's Amap.
So far Muse CLI seems disappointing from a UX perspective.
Spark is decent, I would put it ~similar to Astra Medium but the model is just so slow, you can tell it’s a product of the current “long horizon” rl meme
Typical for it to take 30+ mins on routine work.
Cofounders hate this one simple trick!
Loving how fast it is to force merge into main with my new setup















