iKrasinski

[iKrasinski @ikrasinski]

@trikcode ALL, and add Gemini 2.5 Pro

[iKrasinski @ikrasinski]

@measure_plan @threejs Vibe coding?

[iKrasinski @ikrasinski]

@NickADobos @Firebase True.

[iKrasinski @ikrasinski]

@ProductHunt 1 000 code - 1 030 000 debug

[iKrasinski @ikrasinski]

@gnukeith Ladybird needs to be built? Not to install?🫣

[iKrasinski @ikrasinski]

Prompt: Build a nostalgic Tank 1990/Battle City game in 3D!

- @v0
- @boltdotnew
- @lovable
- #FirebaseStudio
- @Rosebud_AI

[Luma @LumaLabsAI]

World monuments, anime-style.
Made with #Ray2 Camera Motion Concepts.
#aivideo #anime #travel

[iKrasinski @ikrasinski]

@aisdk `{"mcpServers": {...}}` Is it fully compatible with `mcpServers`?

[iKrasinski @ikrasinski]

Multiplayer game by @GeminiApp after 1,000,000 tokens context.

[iKrasinski @ikrasinski]

@flavioAd Always error, and not fix.

[iKrasinski @ikrasinski]

@sama 👀

[Majid Manzarpour @majidmanzarpour]

Excited to release the Vibe Coding Starter Pack for 3D multiplayer web games!

🚀 Built with @reactjs, @threejs & @spacetimedb
👥 Instant multiplayer functionality
🤖 AI-friendly codebase for @cursor_ai
⚡️ Zero setup required—just clone and code!

Get building: https://t.co/GlTPHbF0FL

[AshutoshShrivastava @ai_for_success]

POV: When ChatGPT replies, “I couldn’t generate the image because the request violates our content policies.” https://t.co/gWMz44310T

[iKrasinski @ikrasinski]

@marclou @DataFast_ You bribe with this kind of design.

[AI SDK @aisdk]

The AI SDK now supports speech-to-text with the new transcribe function.

[Tyler Shukert @dshukertjr]

@ikrasinski Source code all avaiable on the Realtime landing page right here: https://t.co/QPwvQGGJyX

[iKrasinski @ikrasinski]

@dshukertjr Hey, please source codes.

[AI at Meta @AIatMeta]

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 with 16 experts.
• Industry-leading context window of 10M tokens.
• Outperforms Gemma 3, Gemini 2.0 Flash-Lite and Mistral 3.1 across a broad range of widely accepted benchmarks.

Llama 4 Maverick
• 17B-active-parameter model with 128 experts.
• Best-in-class image grounding with the ability to align user prompts with relevant visual concepts and anchor model responses to regions in the image.
• Outperforms GPT-4o and Gemini 2.0 Flash across a broad range of widely accepted benchmarks.
• Achieves comparable results to DeepSeek v3 on reasoning and coding — at half the active parameters.
• Unparalleled performance-to-cost ratio with a chat version scoring ELO of 1417 on LMArena.

These models are our best yet thanks to distillation from Llama 4 Behemoth, our most powerful model yet. Llama 4 Behemoth is still in training and is currently seeing results that outperform GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM-focused benchmarks. We’re excited to share more details about it even while it’s still in flight.

Read more about the first Llama 4 models, including training and benchmarks ➡️ https://t.co/9G3QgVdCkB
Download Llama 4 ➡️ https://t.co/eVomRvEr0w

[iKrasinski @ikrasinski]

@GeminiApp Create a browser-based 3D game with a flying firefly through the night forest.

[iKrasinski @ikrasinski]

@NizzyABI To use 0 email, you need to have -1 gmail.