Void Editor (YC S24)
@thevoideditor
Followers
839
Following
28
Media
7
Statuses
25
gpt-oss is out! we made an open model that performs at the level of o4-mini and runs on a high-end laptop (WTF!!) (and a smaller one that runs on a phone). super proud of the team; big triumph of technology.
2K
4K
46K
We did not launch a token. If you see a token under our name, it is an impersonation- please report it.
0
1
8
@0xVoidDev Whatever this is, it is not affiliated with Void Editor (@thevoideditor). This is an impersonation scam, please report.
0
1
4
🚀 Hello, Kimi K2! Open-Source Agentic Model! 🔹 1T total / 32B active MoE model 🔹 SOTA on SWE Bench Verified, Tau2 & AceBench among open models 🔹Strong in coding and agentic tasks 🐤 Multimodal & thought-mode not supported for now With Kimi K2, advanced agentic intelligence
279
1K
7K
Ollama can now think! 🤔🤔🤔 For thinking models, and especially useful for very thoughtful models like DeepSeek-R1-0528, Ollama can separate the thoughts and the response. Thinking can also be disabled! This is useful for getting a direct response. This works across
57
197
1K
Soon coding won't be about looking at code, it will be about looking at the handful of agents writing your code. Parallel agents are coming to Void, and I already use them more than not.
2
1
14
10M tokens is crazy. Large context isn't the human way to go, but it might perform better than 3.7/tool use models until they can forget things and manage their own context. If you want to try Llama 4 on your codebase in a Cursor-style IDE (for free), check out @thevoideditor.
Today is the start of a new era of natively multimodal AI innovation. Today, we’re introducing the first Llama 4 models: Llama 4 Scout and Llama 4 Maverick — our most advanced models yet and the best in their class for multimodality. Llama 4 Scout • 17B-active-parameter model
0
1
11
Checkpoints are coming! Super easy to jump between versions in the next release.
0
1
13
🚀 DeepSeek-V3-0324 is out now! 🔹 Major boost in reasoning performance 🔹 Stronger front-end development skills 🔹 Smarter tool-use capabilities ✅ For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink” 🔌 API usage remains unchanged 📜 Models are
683
2K
12K
Today, we release QwQ-32B, our new reasoning model with only 32 billion parameters that rivals cutting-edge reasoning model, e.g., DeepSeek-R1. Blog: https://t.co/zCgACNdodj HF: https://t.co/pfjZygOiyQ ModelScope: https://t.co/hcfOD8wSLa Demo: https://t.co/DxWPzAg6g8 Qwen Chat:
478
1K
9K
Get access to Void's beta release in our Discord server:
discord.com
The open source AI code editor. | 12663 members
0
0
1
Void is almost ready for release. Make sure you're on the waitlist!
0
0
11
Ollama 0.5 is here with structured outputs! This makes it possible to constrain a model’s output to a specific format defined by a JSON schema. Some examples include: - Parsing data from documents - Extracting data from images - Structuring all language model responses - More
49
361
3K
🚀 DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power! 🔍 o1-preview-level performance on AIME & MATH benchmarks. 💡 Transparent thought process in real-time. 🛠️ Open-source models & API coming soon! 🌐 Try it now at https://t.co/v1TFy7LHNy
#DeepSeek
262
789
4K
Qwen 2.5 coder models are updated with significant improvements in **code generation**, **code reasoning** and **code fixing**. The 32B model has competitive performance with OpenAI's GPT-4o. 32B: `ollama run qwen2.5-coder:32b` 14B: `ollama run qwen2.5-coder:14b` 7B:
ollama.com
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
Super excited to launch our models together with one of our best friends, Ollama! Today, the Qwen capybara codes together with Ollama! @ollama
27
122
788
6k stars in 5 days 🚀 There's a clear need for what we're building. Big things coming soon.
4
2
33