@ShivamAror94788 @Star_Knight12 Did they also open sourced their training dataset and pipeline code ?
English
Andha kanoon
125 posts
Andha kanoon
@Big_With_DB
One prompt man | Founding engineer @thesysdev | Maintainer - OpenUI
Beigetreten Ekim 2021
49 Folgt13 Follower
@Star_Knight12 gemma4?? especially for its size and also its truly open source not just open weight
English
@spiritbuun better idea is to just switch to opus 4.5, anyways i felt opus 4.6 not that great compared to opus 4.5
--model claude-opus-4-5
English
Andha kanoon retweetet
My X bookmarks have an "intellectual shape"
Apparently mine is: Technique-heavy, Tool-obsessed, Light on Opinion
I didn't know until I ran the numbers
OSS I've been building w/@LangChain to explore Generative UI with @thesysdev & @andrewfarah's fieldtheory-cli sqlite db
Andrew Farah@andrewfarah
sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify
English
Andha kanoon retweetet
1/ Got a flood of 'how to build that?' DMs on the dashboard demo
Short answer: OpenUI Lang v0.5.
It's the layer that lets the agent go beyond rendering UI and actually wire up a working app.
State, Data & Actions - the three building blocks for real Generative UI
Rabi Shanker Guha@rabi_guha
Replacing dashboards with a chatbar was step one Here's what step two could look like (Inspired by @Basedash - they've been building in this space for a while)
English
Andha kanoon retweetet
Did Chat kill Dashboards in SaaS?
Rabi Shanker Guha@rabi_guha
1/ Got a flood of 'how to build that?' DMs on the dashboard demo Short answer: OpenUI Lang v0.5. It's the layer that lets the agent go beyond rendering UI and actually wire up a working app. State, Data & Actions - the three building blocks for real Generative UI
English
Andha kanoon retweetet
7/ v0.1 solved: how do LLMs generate UI?
v0.5 solves: how do LLMs generate apps?
Generative UI isn't just about rendering forms and charts in chat. It's real software - composed by the agent, rendered by your components.
Try it out → openui.com/demo/github
English
English
@sarahwooders "Mythos, clone Letta API. Make no mistakes."
English
The new Anthropic managed agents API is basically the Letta API that we've had since a year ago, but closed source and with provider lock-in. They even have read-only memory blocks and memory block sharing -- something which was unique to the Letta agents for a long time.
Funny enough, we actually don't think this is the direction agents are going to go. Having API interfaces for memory blocks and tools is certainly convenient - you can spin up stateful agents as API services with just a few lines of code. But its also limiting: LLMs today are extremely adept at computer-use, and representing their memories in this way limits the action space of agents and their ability to learn.
It's important to remember that just because something comes out of a frontier lab, doesn't mean its the "right" answer long-term. The Letta API ~1 year ago was somewhat of an antipattern in a sea of agent framework libraries offered by every lab. But now, stateful agent APIs are becoming the new norm - especially as providers try to lock in memory/state into their platforms to increase switching costs (which is exactly why we believe memory should live outside of model providers)
If you want to see what the future is going to look like, follow @Letta_AI
Claude@claudeai
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.
English
Andha kanoon retweetet
hmm...why @tan_stack and not gstack
Railway@Railway
We moved Railway's entire frontend off Next.js. Two PRs, zero downtime. Builds went from 10+ minutes to under two. 200+ routes on @vite_js + @tan_stack Router, instant HMR, and dev server startup in seconds. @vrzgc's full breakdown: blog.railway.com/p/moving-railw…
English
Andha kanoon retweetet
Replacing dashboards with a chatbar was step one
Here's what step two could look like
(Inspired by @Basedash - they've been building in this space for a while)
Rabi Shanker Guha@rabi_guha
notice something? Linear, PostHog, Attio - all shipped the same thing in the last few weeks. Homepage is a chat bar - not a dashboard. This is the SaaS industry quietly admitting that traditional UI doesn't work anymore. Every user is different. One homepage can't serve them all. The playbook is shifting: → expose your core APIs → connect an agentic layer → let users use software the way they want SaaS became chat. Chat will become Generative UI - the agent won't just reply in text, it will compose the interface itself. We're closer than people think.
English
Andha kanoon retweetet
This really blew up
Reaction was split so I wrote an article about what's actually happening and where we're headed
x.com/rabi_guha/stat…
Rabi Shanker Guha@rabi_guha
English
Andha kanoon retweetet
Andha kanoon retweetet
Lot of debates on this shift.
Sharing our learnings from building @Razorpay's AI-first dashboard.
<5% of B2B users open a dashboard to explore - most come with a question, but spend time figuring out how to get the answer.
AI-first flips this: just ask for what you need.
We’re starting with a middle path:
– chat as primary
– common actions below
Still beta (opt-in), with ability to switch back.
Ultimately, users decide what sticks.
Rabi Shanker Guha@rabi_guha
notice something? Linear, PostHog, Attio - all shipped the same thing in the last few weeks. Homepage is a chat bar - not a dashboard. This is the SaaS industry quietly admitting that traditional UI doesn't work anymore. Every user is different. One homepage can't serve them all. The playbook is shifting: → expose your core APIs → connect an agentic layer → let users use software the way they want SaaS became chat. Chat will become Generative UI - the agent won't just reply in text, it will compose the interface itself. We're closer than people think.
English
Andha kanoon retweetet
The post was about Generative UI and the future of chat. Not about Linear
Karri Saarinen@karrisaarinen
My favorite thing is how these screenshots fail to show that there’s an entire navigation sidebar and entire product view next to this one screen. (also a preference to pick any screen you like as your start screen)
English
Andha kanoon retweetet
Andha kanoon retweetet
There is a growing tension between logging into SaaS and integrating said SaaS MCP in OpenClaw
OpenClaw is this kind of crap interface. It's actually crappier in a lot of ways but it serves a purpose and people seem to care enough about the purpose to be willing to tolerate the crap interface
ThePrimeagen@ThePrimeagen
I am so so so very tired of this crap interface
English
Andha kanoon retweetet
Andha kanoon retweetet
notice something?
Linear, PostHog, Attio - all shipped the same thing in the last few weeks. Homepage is a chat bar - not a dashboard.
This is the SaaS industry quietly admitting that traditional UI doesn't work anymore. Every user is different. One homepage can't serve them all.
The playbook is shifting:
→ expose your core APIs
→ connect an agentic layer
→ let users use software the way they want
SaaS became chat. Chat will become Generative UI - the agent won't just reply in text, it will compose the interface itself.
We're closer than people think.
English