Life has treated me well and I am thankful.
San Francisco, CA
Joined June 2008
- Tweets15K
- Following370
- Followers7.6K
- Likes13K
Dan Levine retweeted
if you want this in your own apps ASAP, sign up for Modem and use our feedback API (there's a free plan)
we give you a prompt to one-shot a feedback form inside your app
then tell Modem what you want to happen when feedback arrives - like auto-build features or alert your team
I'm now building an "improvements" feature into all of my personal vibecoded applications: a freeform text input that's hooked up to an agent that yolo implements whatever is submitted.
It's an interesting experience -- the activation energy barrier to sanding any rough edge or implementing any new feature becomes extremely low. Someone else who uses one of the applications I created has already implemented 150 improvements over the course of a few days. This pattern feels like a new kind of tool -- liquid software? -- and every application that doesn't have this feature now has a slightly rigid and anachronistic flavor. Why can't I just tell it how I want it to be different?
Now, it's not obvious to me how this pattern can or should scale. Does it become unmaintainable after a while? (Maybe model intelligence improvement outstrips my feature appetite such that it's fine?) How does collaborative software work in this model? Can software designed this way be secure and reliable?
Whatever the larger questions about broader deployment, it definitely works great in a personal context. It reminds me a little of the visions of Lisp/Lisp machines, Smalltalk, and HyperCard -- systems that the user can take control of and modify. Those visions never quite worked, though: the vast majority of software today is not end-user modifiable in any useful way. So, while this "liquid" affordance is a very small touch, the way it changes one's relation to the software feels a bit transgressive and empowering in a Lickliderian and Engelbartian way.
Dan Levine retweeted
Reinvesting / contributing money into San Francisco is the obligation of all who made their money here. We have a responsibility to current and future generations.
please don't show this to my wife or she'll buy even more Halloween animatronics... and fast... 1.8s...
today we are announcing openrouter for commerce: opencommerce.sh
a single endpoint that integrates 5k stores, including Doordash, Amazon and most shopify stores, with payments using Agentcard (Stripe Link and Shop coming soon).
we built opencommerce to solve 3 problems:
* coverage: one endpoint to integrate 5k stores. agentic purchasing is a core feature for most personal assistants, but not their main business. searching for products and buying on behalf of users shouldn’t be as painful as it is today (e.g. it shouldn’t involve browser automations or dealing with PSPs). opencommerce solves that: 1 tool, every online store.
* reliability: 100% uptime. the challenge with browser automations is that they fail (e.g. captchas, bot-detection, etc). we run thousands of tests every couple of hours on every one of the stores to guarantee that the integration works when your user tries to buy something.
* speed: responses in under 10s. consumers are used to Amazon speed, and agentic purchases have so far felt like a downgrade. most agents spend minutes finding products before they come back with results. we monitor speed and improve it constantly.
Dan Levine retweeted
today we are announcing openrouter for commerce: opencommerce.sh
a single endpoint that integrates 5k stores, including Doordash, Amazon and most shopify stores, with payments using Agentcard (Stripe Link and Shop coming soon).
we built opencommerce to solve 3 problems:
* coverage: one endpoint to integrate 5k stores. agentic purchasing is a core feature for most personal assistants, but not their main business. searching for products and buying on behalf of users shouldn’t be as painful as it is today (e.g. it shouldn’t involve browser automations or dealing with PSPs). opencommerce solves that: 1 tool, every online store.
* reliability: 100% uptime. the challenge with browser automations is that they fail (e.g. captchas, bot-detection, etc). we run thousands of tests every couple of hours on every one of the stores to guarantee that the integration works when your user tries to buy something.
* speed: responses in under 10s. consumers are used to Amazon speed, and agentic purchases have so far felt like a downgrade. most agents spend minutes finding products before they come back with results. we monitor speed and improve it constantly.
Dan Levine retweeted
Funding rounds aren't milestones. It shouldn't be your goal to raise a series A. It should be your goal not to need to.
Dan Levine retweeted
@scale_ai is teaming with @huggingface to make robots better at long, multi-step tasks, and we’re open-sourcing all of it!
Today @scale_AI is launching FineART-VLA, a model that helps robots complete longer tasks, building on our first open-source robotics dataset.
Built with @huggingface 's LeRobot team, this is Scale’s first open-source robotics release.
Thanks to @Thom_Wolf + team for the partnership.
The momentum on open-source robotics is picking up steam, and high-quality data will determine how far it goes. Go build!
labs.scale.com/blog/fineart
Dan Levine retweeted
Introducing Vercel CI
• Intelligently skips tasks with Turborepo
• 2-6× faster CI in our internal repositories
• Optimized for agents via Vercel MCP and CLI
After nearly 8 million tasks, we're excited for the future of agentic CI. In beta on all plans.
vercel.com/blog/introducing-…
Dan Levine retweeted
MikeOSS 2.0 is here: a free open-source AI harness for legal work which you can self-host, connect to any model, or run fully local.
What’s new in 2.0:
- Integrated Drafting Interface (IDE): a Cursor for legal UI with a file explorer, document viewer/editor & chat side by side
- Word add-in + workflows in Word
- Subagents for big reviews
- Web search
- Memory (account and project scoped)
- Side chat
- Slash commands
- Orgs & audit logs
- Wider model provider support: Azure, Bedrock, @grok, @vercel AI Gateway, @MistralAI, @OpenRouter, @opencode Go and more
- Local AI with Ollama integration
Website: mikeoss.com (link to github on main page)
Thank you to all contributors, including @solirvine @Pabz @b1rdmania @Diya_555696 @BitGrateful @SadhakaDev @b1rdmania @antoinelouis_ @snowyukitty
Dan Levine retweeted
Anthropic discloses only one venture capitalist in its S-1 filing: 37-year-old Yasmin Razavi. The Spark Capital GP is also the only VC backer who holds a board director seat.
bloomberg.com/news/articles/…
Dan Levine retweeted
Carmack on Goose:
That looks really neat! The automatic analysis and use of multiple data stacks and resizable fields takes it from "lots of work can be done this way" to "basically everything can be".
The relative references and built in binary structure validation also enable direct memory mapping of data structures and immediate use of network data. "Parsing" file and network data is often 100x slower than it needs to be.
Dan Levine retweeted
we've hired two new helpers for our dinner party: here's steve and miranda pouring pink lemonade for each guest fully autonomously, via a fine-tuned pi0.5 policy 🍋
@lucyjcai and i are testing all kinds of robot control in our quest to host the most robotic dinner party.
Dan Levine retweeted
Announcing Dagger 1.0 beta.
Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens.
Featuring: test-native CI, dev shells, local and remote execution, official modules, and more.
dagger.io/blog/dagger-10-bet…
Dan Levine retweeted
When credentials are stored in @1Password and AI agents need to use them on websites, @usekernel is the internet runtime that makes the handoff secure and simple in the browser.
Developers can start building with 1password + Kernel agentic autofill today, we are excited to be a launch partner with 1Password for Agents.
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
Dan Levine retweeted
Vercel now has all the pieces in place to host at-scale backends.
WebSockets, Queues, Workflows, Cron, Services, Containers, Python, Daemons, Long-duration Functions, Blob, Drives, Sandbox…
Any guesses what comes next?
WebSocket support in Vercel Functions is now generally available.
Vercel now serves 15 million WebSocket connections a day across AI chat, streaming, and realtime multiplayer apps.
vercel.com/changelog/websock…
