How do you tell whether a model is actually noticing its own internal state instead of just repeating what training data said about thinking? In a latest Anthropic’s research study ‘Emergent Introspective Awareness in Large Language Models‘ asks whether current Claude models can do more than talk about their abilities, it asks whether they can…
!pip install -q pyspark==3.5.1 from pyspark.sql import SparkSession, functions as F, Window from pyspark.sql.types import IntegerType, StringType, StructType, StructField, FloatType from pyspark.ml.feature import StringIndexer, VectorAssembler from pyspark.ml.classification import LogisticRegression from pyspark.ml.evaluation import MulticlassClassificationEvaluator spark = (SparkSession.builder.appName(“ColabSparkAdvancedTutorial”) .master(“local[*]”) .config(“spark.sql.shuffle.partitions”, “4”) .getOrCreate()) print(“Spark version:”, spark.version) data = [ (1, “Alice”, “IN”, “2025-10-01”, 56000.0, “premium”), (2, “Bob”, “US”,…
How can a small model learn to solve tasks it currently fails at, without rote imitation or relying on a correct rollout? A team of researchers from Google Cloud AI Research and UCLA have released a training framework, ‘Supervised Reinforcement Learning’ (SRL), that makes 7B scale models actually learn from very hard math and agent…
OpenAI has released a research preview of gpt-oss-safeguard, two open weight safety reasoning models that let developers apply custom safety policies at inference time. The models come in two sizes, gpt-oss-safeguard-120b and gpt-oss-safeguard-20b, both fine tuned from gpt-oss, both licensed under Apache 2.0, and both available on Hugging Face for local use. https://openai.com/index/introducing-gpt-oss-safeguard/ Why Policy-Conditioned…
In this tutorial, we build an Agentic Data and Infrastructure Strategy system using the lightweight Qwen2.5-0.5B-Instruct model for efficient execution. We begin by creating a flexible LLM agent framework and then develop specialized agents that handle different layers of data management, from ingestion and quality analysis to infrastructure optimization. We integrate these agents into an…
How do you build a language model that grows in capacity but keeps the computation for each token almost unchanged? The Inclusion AI team from the Ant Group is pushing sparse large models in a methodical way by releasing Ling 2.0. Ling 2.0 is a reasoning based language model family built on the idea that each…
In this tutorial, we explore how we can build an autonomous agent that aligns its actions with ethical and organizational values. We use open-source Hugging Face models running locally in Colab to simulate a decision-making process that balances goal achievement with moral reasoning. Through this implementation, we demonstrate how we can integrate a “policy” model…
Small models are often blocked by poor instruction tuning, weak tool use formats, and missing governance. IBM AI team released Granite 4.0 Nano, a small model family that targets local and edge inference with enterprise controls and open licensing. The family includes 8 models in two sizes, 350M and about 1B, with both hybrid SSM…
How do you convert real agent traces into reinforcement learning RL transitions to improve policy LLMs without changing your existing agent stack? Microsoft AI team releases Agent Lightning to help optimize multi-agent systems. Agent Lightning is a open-sourced framework that makes reinforcement learning work for any AI agent without rewrites. It separates training from execution,…
Can a compact late interaction retriever index once and deliver accurate cross lingual search with fast inference? Liquid AI released LFM2-ColBERT-350M, a compact late interaction retriever for multilingual and cross-lingual search. Documents can be indexed in one language, queries can be written in many languages, and the system retrieves with high accuracy. The Liquid AI…
