Kartik retweeted
Karpathy's examples assume people will manage API keys, but no one wants to sign up for 100+ of services!
I asked Mercator to "make a 3b1b explainer video"
It found a voice, research, and video API and paid them each a few cents - way easier to think about
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Kartik retweeted
OUSD by @openstandard gives businesses a new stablecoin option on Tempo, combined with enterprise features for real-world payments:
• Private balances and payments via Tempo Zones
• 1:1 conversion to USD and competitive FX
• Build earn products that tap into deep liquidity
Kartik retweeted
Open USD (OUSD) is live on Tempo, with $400M+ in liquidity at launch.
Issued natively on Tempo, OUSD by @openstandard gives businesses a new stablecoin for payments, settlement, and treasury, with liquidity deployed across decentralized exchanges, stablecoin swaps, and bridges.
Found a fun new use case for Muse: messaging my FIL.
He only speaks Korean so it’s been tedious translating back-and-forth. We moved our conversation to IG DMs through Muse and it’s been great so far.
Muse notifies me whenever he messages me with it already translated. I can then iterate on a response with Muse and send it back to him in Korean!
Don’t even need to open IG.
Kartik retweeted
INTRODUCING MERCATOR by @tempo.
Mercator gives agents a new effort level.
By giving an agent a search engine to the world's paid tools it empowers a small model to punch above its weight, while being cheaper than larger models.
$5 Mercator credits w/ your X/Github ⬇️
Muse helped me buy a cake for my wife in Seoul from an indie IG shop she’s a fan of. I don’t speak Korean well (yet) so this usually would have been much harder.
Worst part was actually paying for it as a foreigner. Kept going between Muse and Kakao to figure out an acceptable payment method with her (and we eventually did).
We both initially connected through IG so would have been nice to just have Muse pay her directly (stablecoins on @tempo 😏) rather than exiting to other apps.
In general, I’m extremely bullish on personal agents for travel as these things get even more frictionless to use.
Have switched to Muse since launch and it’s an overall way better experience due to being it’s own native app. I’m a sucker for the minor delightful details and having access to Instagram bookmarks is huge.
Had Instinct export our conversation so Muse was able to just carry on from it.
Have been using Instinct with location sharing while traveling in Korea and it’s been a magical experience.
My wife and I roughly curated a list of places we wanted to go to and then have been letting Instinct fill in the gaps. Hasn’t disappointed yet.
Location sharing on Instinct
Starting today, you can share your location with Instinct on iMessage. Instinct can recognize when you arrive somewhere, and answer questions about where you’ve been.
Here are some examples of how our early alpha group uses it:
- Ordering food to your current location
- Finding a lunch spot a few minutes away based on what you like
- Guiding you through a trip itinerary in a new city
- Figuring out how to get home, including which train to catch and where to board
Instinct can also act when you enter or leave an area. You can ask it to remind you to pick up your package when you get home, or have your boarding pass ready when you arrive at the airport. These location triggers let Instinct follow up when the task becomes relevant.
Your location history also gives Instinct context to answer questions like “Where did I park?”, “How long did my bike ride take?”, or “What was that nice coffee shop around here that I went to last month?”
If you’re an existing user, you can try it today by asking Instinct to request your location. If not, we’re giving access to 1000 new users who want to try it out: app.instinct.com/invite?t=lo… . If you missed it, you can join our waitlist here: app.instinct.co/login.
Kartik retweeted
Tempo's goal is to increase the velocity of money in this brave new world.
We're building the base layer: a chain that can reach tens of thousands of transactions per second, at a fraction of a cent, so that money can move at the speed of agents.
Join us.
Between wallets for agents with @link (and @privy), MPP, Tempo, MCP, Stripe CLI, Agentic Commerce Suite, sandboxes, OpenRouter, Metronome/metered billing, Radar and distillation/token fraud, it turns out that "the economic infrastructure for AI" implicates a lot. Pretty much every layer of the Stripe stack is changing, and it’s a very good time to join if you want to build high-scale software that facilitates the practical deployment of this new intelligence.
Kartik retweeted
Announcing Centaur 2.0!
Centaur is frontier, agentic infrastructure that you own. Centaur is like Claude Tag, but open source and on steroids.
Centaur 2.0 can connect to everything you have access to, and can reason over it next to where you work, either in Slack, Discord, Teams or in your local Codex or Claude Code via an MCP.
But context isn't useful if it can be accessed by anyone, so we rebuilt Centaur from the ground up for security. Centaur obviously doesn't have access to secrets because we're leveraging egress proxies.
Centaur 2.0 takes that a step further enabling administrators to configure who can access what from where. This means that Centaur can have access to private information that you normally wouldn't feel comfortable giving it access to (e.g. DMs or sensitive channels and docs) but only expose it to authorized principals.
It also means you can add Centaur to external channels and leverage it as a virtual colleague that doesn't live only in your Slack, for example, but also your Slack Connect channels! This is extremely powerful as we start moving to a world where agents cross organizational boundaries.
Also in case anyone's wondering, yes we rewrote it in Rust! Centaur is now way way more stable at durably executing threads, and its workflow engine is now based on Absurd.
We have been operating Centaur since January, officially launched and Open Sourced it in May, and now we're full speed towards making it the #1 open source agentic infrastructure.
To succeed at that, I'm thrilled to welcome @mslipper to the @paradigm team who will be leading all our Applied AI work, while continuing to maintain and extend Iron Proxy as the leading secure secret access for agents. Welcome Matt, it's an honor after all these years of knowing you!
Read the full blogpost below, and apply to join our team!
