b71 @b71eth

Hello world 👋. We set out to be a project driven by open standards, open source, and extensibility. Check out the app and repo and let us know your ideas.

Nick Gomez @nickgomez

6 hours ago

Introducing @openknowledge, the best markdown IDE for humans and agents. Open source. Local and private. LLM-wiki ready. Use with Claude, Codex, and your favorite agent today.

18 61 667 63K 986

1 2 11 4K 18

View Details

b71 @b71eth

3 hours ago

@dabit3 @DevinAI If competition keeps intensifying, I think it'll drop to around $1.

0 0 0 76 0

View Details

We’re launching the first in a series of Embodied Reasoning offerings: Perceptron Egocentric. It achieves SOTA over the best robotic annotation pipelines built on Gemini 3.5 Flash and Gemini Robotics-ER 1.6. Early access is available to partners.

3 13 58 25K 41

View Details

b71 @b71eth

4 hours ago

@MatthewBerman If competition heats up even more, I guess we'll be able to use Fable for next to nothing. :)

0 0 0 23 0

View Details

b71 @b71eth

4 hours ago

@ClaudeCodeLog

0 0 0 149 0

View Details

b71 @b71eth

7 hours ago

@poolsideai @ollama 🫡

0 0 0 22 0

View Details

Poolside @poolsideai

7 hours ago

Big day for @ollama, and a big day for open models. We’re proud to build with partners making open models easier to access for everyone.

ollama @ollama

9 hours ago

Big day for Ollama! When we started, open models and the open source AI ecosystem were in their early days with few believers. Our belief in open source has never wavered. With today's fundraising announcement and our 9M+ active builders, we’re ready to scale open models into

147 155 1K 147K 122

2 3 29 1K 0

View Details

b71 @b71eth

7 hours ago

@boardyai 🤫

1 0 0 31 0

View Details

Steeve Morin @steeve

2 days ago

We're releasing ZML/LLMD, our homegrown LLM server built on top of our homegrown high performance heterogeneous inference stack. It ships with 5 architectures out of the box: NVIDIA, AMD, Metal, Intel and TPU. All transparent. It supports DFlash, continuous batching, prefix caching, the whole deal. Oh, and it's fast.

ZML @zml_ai

2 days ago

x.com/i/article/2074…

6 27 130 87K 52

27 58 281 56K 102

View Details

Eiso Kant @eisokant

2 days ago

Exciting! Working closely with the ZML crew to get Poolside models on here quickly. Pretty wild to have this much silicon support and no compilation at runtime. Just a single container that works.

Steeve Morin @steeve

2 days ago

27 58 281 56K 102

0 4 44 4K 4

View Details

jack @jack

a day ago

ai-fed, human-finished.

648 582 6K 596K 589

View Details

Poolside @poolsideai

a day ago

Good to see Laguna XS 2.1 clear the board 💙

atomic.chat @atomic_chat_hq

a day ago

Laguna XS 2.1 performed on Qwen 3.6 35B's level in Tetris building and ran 2x faster We tested two open models on a single RTX 3090 in the @poolsideai coding agent. The task was building a playable retro Tetris as one self-contained html file. Each model wrote and rewrote the

15 25 226 22K 138

0 3 40 3K 8

View Details

Poolside @poolsideai

3 days ago

Poolside is coming to @RaiseSummit Tomorrow @eisokant joins two panels that are very close to what we’re building toward: training AI at scale, and making the open ecosystem stronger. Tune in: Training at Scale: What a Frontier Lab Actually Needs 1:00 PM–1:40 PM - IREN AI Cloud Lounge With @axiommathai, @Prior_Labs, @fieldai_, @felicis From Research to Reality: Why Open Source Is the Engine of AI Innovation 4:20 PM–5:00 PM - Grace Hopper Stage With @arena, @huggingface, @NousResearch, @bfl_ai

0 3 14 7K 2

View Details

b71 @b71eth

4 days ago

@smakosh 🫡

0 0 1 51 0

View Details

b71 @b71eth

4 days ago

@jrysana @ibocodes

0 0 0 121 0

View Details

Paul Kinlan @Paul_Kinlan

6 days ago

How might a Lighthouse testing tool work with LLMs and Agent harnesses. aifoc.us/how-might-a-mo… I had a lot of fun building this, and I think that this is one very useful and practical way web dev, loops and goals will change this year.