E01

LLM LAUNCHPAD. Beyond the chatbox. Built launch demos & new use-cases with foundation-model teams. Pushing models to the edge — or breaking them for what's next

[E01 @e01ai]

Been building the demos behind model launches you've probably seen — quietly, with some great model teams. So many possibilities, poked and pushed and tested.

Sharing the work here now. 🧵 — Mike Luan, e01

[E01 @e01ai]

⚡️ Step-3.7-Flash launch — pushed this flash-class model to the edge w/ @stepfun_ai.

Built Pointy (a second cursor that explains whatever you're looking at) + a set of parallel-research demos 👇

https://t.co/5AOqu1yEDi

Write up here:
https://t.co/iiGCZ7QYF6

[E01 @e01ai]

With launch of Step 3.7 Flash by @StepFun_ai , we explored multiple new use-cases with "Flash Class" models.
The balance of speed, cost and quality gives life to new way to interact with the model.

This demo shows possibility to "Sample" the model in realtime, revealing layer of intelligence instead of a single "chat".

Write up coming soon.

[E01 @e01ai]

Been building the demos behind model launches you've probably seen — quietly, with some great model teams. So many possibilities, poked and pushed and tested.

Sharing the work here now. 🧵 — Mike Luan, e01

[E01 @e01ai]

consensus — ask once, a crowd of personas answers in parallel, weighted into one view. A model as a population, not a single reply. Built on GLM-5.1-Fast (+ other models) 👇

https://t.co/eqRW9K74E9

https://t.co/OBAQdRuBNv

[E01 @e01ai]

lean & fast models + fast infra do make a difference.

in our latest experiment {consensus}, 50~100 persona (agents) are generated to answer one question.

turning "query" into "sampling", to potentially "extract" more from the model offerings.

https://t.co/eqRW9K74E9

repo:
https://t.co/D1QVwhF6Hu

[E01 @e01ai]

A Lab note for Step 3.7 Flash launch.
--
When Flash models bring speed, cost, and intelligence into the “usable” range all at once, the way intelligence is supplied changes structurally.
--
https://t.co/WI9k8GwYiR

[E01 @e01ai]

@TheAhmadOsman Yes, pretty good! Toolcall consistency is high

[E01 @e01ai]

Adding to the "Sampling the Model" Track, Parallel requests to Step-3.7-Flash with cluster of persona, voting in realtime.

[E01 @e01ai]

@StepFun_ai High speed, low cost and good quality + multi modal make latest "Flash" models a unique new class.

Harness are made for pro-models, Flash model turn all App into their harnesses.

https://t.co/VD9QGZOeXw

[E01 @e01ai]

With launch of Step 3.7 Flash by @StepFun_ai , we explored multiple new use-cases with "Flash Class" models.
The balance of speed, cost and quality gives life to new way to interact with the model.

This demo shows possibility to "Sample" the model in realtime, revealing layer of intelligence instead of a single "chat".

Write up coming soon.

[E01 @e01ai]

With launch of Step 3.7 Flash by @StepFun_ai , we explored multiple new use-cases with "Flash Class" models.
The balance of speed, cost and quality gives life to new way to interact with the model.

This demo shows possibility to "Sample" the model in realtime, revealing layer of intelligence instead of a single "chat".

Write up coming soon.

[E01 @e01ai]

@jietang amazing performance, opens up new way to interact with the model.
from "chat" to "sampling" the latent of intelligence.
built during testing phase. - https://t.co/uK7X4cCrOF

[E01 @e01ai]

lean & fast models + fast infra do make a difference.

in our latest experiment {consensus}, 50~100 persona (agents) are generated to answer one question.

turning "query" into "sampling", to potentially "extract" more from the model offerings.

https://t.co/eqRW9K74E9

repo:
https://t.co/D1QVwhF6Hu

[E01 @e01ai]

We've added support for more model providers (openrouter | fireworks | gemini) to vcanvas and pushed source to github.

Grab the source here: https://t.co/wzQ1ZZRx99

Play with more providers here: https://t.co/huUtlGD4UG

Enjoy!

[E01 @e01ai]

We'll add more models / providers to vcanvas playground soon. https://t.co/UyotpQCWyu

[E01 @e01ai]

@googlegemma Could not believe a 31B Model did this. Multi-modal input, single shot, generative art style. Local, on-device..

[E01 @e01ai]

@googlegemma Could not believe a 31B Model did this. Multi-modal input, single shot, generative art style. Local, on-device..

[E01 @e01ai]

@Seraphine_Moyao @berryxia 多模态Coding感觉超越。欢迎体验一下，也可以来这里体验launch demo里画画canvas出代码 https://t.co/UyotpQCWyu

[E01 @e01ai]

@witcheer Very fast and capable model, we compared it with Kimi 2.5 turbo while doing the demos and it is on-par, with even higher speed. A long waited one.

[E01 @e01ai]

@lorenzochr @Zai_org Let us wait for official announcement

[E01 @e01ai]

Collaborating with @Zai_org on early exploration around GLM-5V-Turbo (just launched), a strong, fast & multi-modal model.

Richer modality = more creative freedom.

We explored the interface side to enable it: a canvas...

makes visual interaction fluid — draw, collage, iterate, all in one space.

Pair that with 5V-Turbo's coding capability, you get sketch-to-running-code in seconds.

https://t.co/KjfrRHBmHi

[E01 @e01ai]

@Zai_org Experience GLM-5V-Turbo with the canvas in launch demo.

Grab an API key and try it
https://t.co/C3rLRgXoVY

[Z.ai @Zai_org]

Introducing GLM-5V-Turbo: Vision Coding Model

- Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts.
- Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents.
- Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw.

Try it now: https://t.co/WCqWT0qCQb
API: https://t.co/xDy1O6ZPcz
Coding Plan trial applications: https://t.co/qCM6cri0KK