@artificialguybr Profile picture

๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š

@artificialguybr

AI.

Similar User
Morph photo

@morph_labs

Abhi Venigalla photo

@ml_hardware

Clรฉmentine Dominรฉ ๐ŸŠ photo

@ClementineDomi6

Dina Yerlan photo

@dina_yrl

WizardLM photo

@WizardLM_AI

Tanmay Gupta photo

@tanmay2099

Teknium (e/ฮป) photo

@Teknium1

Allen T. photo

@Mr_AllenT

Linus photo

@thesephist

Dhruv Shah photo

@shahdhruv_

๐Ÿ‘ฃKแ—ชแ—ฉแ—ฏG๐Ÿ‘ฃ ๐Ÿ”ถ photo

@Kdawg5000

lachlan photo

@hyprturing

Harris Rothaermel photo

@DeveloperHarris

Moreau Thomas photo

@tomamoral

Simo Ryu photo

@cloneofsimo

Pinned

I've redesigned all my site now using more modern frameworks with greater stability and responsiveness. This is where I put all my projects and where you can get all the information about me. I hope you enjoy it. artificialguy.com

Tweet Image 1

which one is supposed to be the left-wing propaganda machine again?

Tweet Image 1
Tweet Image 2


Crazy to think we're still in Midjourney V6.

Do you think Midjourney v7 will land before Christmas? v6 came out in December 2023.



๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Oh wow! @MSFTResearch released 1 MILLION synthetic instruction pairs covering different capabilities, such as text editing, creative writing, coding, reading comprehension, etc - permissively licensed ๐Ÿ”ฅ Explore it directly on the Hugging Face Hub! Kudos MSFT! Let theโ€ฆ


A lot of people saying good things about the new Cursor competitor, Windsurf from Codeium.


๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

ChatGPT for macOS can now read content from coding apps like VS Code, Xcode, TextEdit and Terminal to provide context-aware answers, available in beta for Plus and Team users

Tweet Image 1

We have a new king.

Massive News from Chatbot Arena๐Ÿ”ฅ @GoogleDeepMind's latest Gemini (Exp 1114), tested with 6K+ community votes over the past week, now ranks joint #1 overall with an impressive 40+ score leap โ€” matching 4o-latest in and surpassing o1-preview! It also claims #1 on Visionโ€ฆ

Tweet Image 1


๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

gemini-exp-1114โ€ฆ. available in Google AI Studio right now, enjoy : ) aistudio.google.com


๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

BREAKING ๐Ÿšจ: A new Gemini exp 1114 model is now publicly available on Google AI Studio ๐Ÿ‘€ Have you tried it yet?

Tweet Image 1

gemini-exp-1114โ€ฆ. available in Google AI Studio right now, enjoy : ) aistudio.google.com



๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Weโ€™ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.


Codeium dropped a new VSCODE fork. With AI tools to challenge Cursor, including a Composer.

Today weโ€™re excited to launch the Windsurf Editor - the first agentic IDE, and then some ๐Ÿ„ In Windsurf, we have given the AI a previously unseen combination of deep codebase understanding, powerful set of tools, and real time awareness of your in-editor actions. The result? Aโ€ฆ



๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

jimmy was right: opus 3.5 didnโ€™t meet expectations and anthropic, while fundraising, quietly removed any mention from their website

Tweet Image 1

If you were trying to raise funds, would you disclose you had a training run failure. Now you rush to do your own o1, but are you too late?



๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Releasing two trillion tokens in the open. huggingface.co/blog/Pclanglaiโ€ฆ

Tweet Image 1

๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Salesforce presents BLIP3-KALE Knowledge Augmented Large-Scale Dense Captions

Tweet Image 1

๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

supervision-0.25.0 line counter is a lot more robust; lets gooo! objects may be small, move quickly, or get occluded itโ€™s easy to build a video analysis that works well for 30 seconds. building one that holds up for 24 hours is a different story. github.com/roboflow/superโ€ฆ


๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

๐Ÿš€ Introducint JanusFlow: harmonizing autoregressive LLMs with rectified flow! By adopting the best practices in both fields, JanusFlow excels at both image understanding & generation in a single model. โšก๏ธ Powerful, simple, flexible, & your next-gen of Janus is here! ๐Ÿ”ฅ ๐Ÿ“„โ€ฆ

Tweet Image 1
Tweet Image 2
Tweet Image 3

๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Today we are launching the Forge Reasoning API Beta, an advancement in inference time scaling that can be applied to any model or a set of models, for a select group of people in our community. nousresearch.com/introducing-thโ€ฆ The Forge Reasoning engine is capable of dramaticallyโ€ฆ

Tweet Image 1

๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

We are looking for a developer to help us fine-tune a modern (mochi, cogvideox) video generation model on inpainting. For the right experience we are open to any salary. Essentially we want to recreate the inpainting examples of this model lumiere-video.github.io/#section_inpaiโ€ฆ If you haveโ€ฆ


Cool, but honestly Supermaven has never had a very good quality for me.

We are excited to announce that @SupermavenAI is joining Cursor! Together, we will continue to build Cursor into a research and product powerhouse. (1/5)



๐‘จ๐’“๐’•๐’Š๐’‡๐’Š๐’„๐’Š๐’‚๐’ ๐‘ฎ๐’–๐’š Reposted

Bug fixes & analysis for Qwen 2.5: 1. Pad_token should NOT be <|endoftext|> Inf gens 2. Base <|im_start|> <|im_end|> are untrained 3. PCA on embeddings has a BPE hierarchy 4. YaRN 128K extended context from 32B 5. Fixed versions + 128K GGUFs: huggingface.co/unsloth Details:โ€ฆ

Tweet Image 1

Loading...

Something went wrong.


Something went wrong.