CODE

→ View original post on X — @learnopencv

Fine-Tuning AnomalyCLIP for Zero-Shot Anomaly Detection

By

@learnopencv

–

01 July 2025 17h36

Fine-Tuning AnomalyCLIP: Class-Agnostic Zero-Shot Anomaly Detection In this week’s deep dive, we explore how AnomalyCLIP, a CLIP-based vision-language model, performs zero-shot and fine-tuned anomaly detection on the TN3K thyroid nodule segmentation dataset. Using a robust

Vertex AI: Google’s Full-Stack ML Platform for Model Training

By

–

01 July 2025 17h35

8. Vertex AI
Google’s full-stack ML platform for pros & beginners alike. → Train, fine-tune, and deploy large models with low-code support. Free: $300 Google Cloud credits http://
cloud.google.com/vertex-ai

Google Text-to-Speech API: Voice Integration for Applications

By

–

01 July 2025 17h35

7. Text-to-Speech API
Give your app a voice.
Standard & WaveNet voices with tone, speed, and language controls. Free:
• 4M chars (standard)
• 1M chars (WaveNet) http://
cloud.google.com/text-to-speech

Firebase AI Studio: Visual AI App Builder Now Free Preview

By

–

01 July 2025 17h35

3. Firebase AI Studio
Visually build and test AI-powered apps inside Firebase.
Prompt-to-UI made easy for dev teams. -> Free for up to 3 workspaces (preview phase)

Google AI Studio: Test Gemini Models Without Code

By

–

01 July 2025 17h35

1. Google AI Studio
Test-drive Gemini models without code.
Prompt, tweak, and export directly into your app.
→ Perfect for developers & tinkerers.

→ View original post on X — @langchain

Multi-modal Researcher with Gemini 2.5 and LangGraph

By

@langchain

–

01 July 2025 17h07

Multi-modal researcher with Gemini 2.5 Generate reports + custom podcasts on any topic w/ LangGraph + Gemini 2.5: • YouTube video processing
• Real-time Google Search integration
• Multi-speaker text-to-speech Repository:
https://github.com/langchain-ai/multi-modal-researcher Video:
https://youtu.be/6Ww5uyS0tXw

→ View original post on X — @openai

OpenAI Reveals ChatGPT Development Behind Scenes Podcast

By

@openai

–

01 July 2025 17h01

OpenAI Podcast Episode 2 is now live! @markchen90 and @nickaturley join @andrewmayne to pull back the curtain on the making of ChatGPT. They also get into how products are developed and what’s next for agentic coding and multimodal assistants.

→ View original post on X — @hardmaru

Pass@2 Scores Gap Below Pass@250 Levels Explained

By

@hardmaru

–

01 July 2025 16h47

The pass@2 scores are actually reported in the blog post, but as mentioned in the parent tweet, the gap is ~ 10-15% below pass@250 levels. What I meant in my previous tweet is to narrow this gap in the future.