Liquid AI released The Antidooman open-source approach that addresses common failure modes in conceptual models. That failure mode is the doom loop. In the doom loop, the model releases the span. It then repeats that span over and over again. Output continues until the content window is finished. Small thinking models are more prone to … Read more
Tencent’s Hy team has been released Hy3. Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model. It opens only 21B parameters per token. Weights go under Apache License 2.0. Hy3 is intended for visualization, agent workflow, and remote content operations. What is Hy3? The Hy3 architecture consists of a small MoE with 192 specialists and 8 high-level … Read more
OpenAI has released two new Realtime models to its API. They are named gpt-realtime-2.1 again gpt-realtime-2.1-mini. Both are aimed at low voice and multimodal experiences. The smaller model is a notable part of this release. It is a small real-time voice reasoning model. Shipping is the same as before gpt-realtime-mini. OpenAI also reduces p95 latency … Read more
banner(“[2/9] BIOACTIVITY MINING (ChEMBL activities -> pIC50)”) def pull_activities(tid, cap): url, rows = f”{BASE}/activity”, [] params = {“target_chembl_id”: tid, “standard_type”: “IC50”, “pchembl_value__isnull”: “false”, “limit”: 1000, “format”: “json”} js = http_json(url, params) pages = 0 while js and pages < 60: rows.extend(js.get(“activities”, [])) pages += 1 if len(rows) >= cap: break nxt = js.get(“page_meta”, {}).get(“next”) if … Read more
Sakana AI has added a new feature called Saka Translate in its chat service, Saka Chat. It handles double translation across Japanese, English, and Chinese. The translation engine says And strategiesa series of company models adapted to Japan. Sakana Translate ships as a free web app. One account opens all … Read more
Visual Language Models, or VLMs, are AI models that can understand both visual content and language. While earlier models such as CLIP and BLIP linked images and text, modern VLMs can analyze images, read documents, interpret charts, answer visual questions, and support multi-channel conversations. Models like GPT-4o, Gemini, Claude Vision, and Qwen-VL make virtual AI … Read more
import importlib.util, os, shutil as _sh if importlib.util.find_spec(“tunix”) is None: print(“Installing Tunix + JAX ecosystem — this takes ~5-8 min…”) %pip install -q ipywidgets tensorboardX transformers grain nest_asyncio %pip install -q datasets huggingface_hub “numpy>2” %pip install -q tensorflow tensorflow_datasets %pip install -q git+ %pip install -q git+ %pip install -q git+ %pip uninstall -q flax … Read more
Meituan released LongCat-2.0a large Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and open about 48 billion per token. The model addresses agent coding: code understanding, generation, and execution within an agent’s workflow. Two facts stand out. First, LongCat-2.0 supports native 1 million token context window. Second, both training and worship continued in … Read more
LlamaIndex published legal-kbpublic reference request on GitHub. It is defined as a database of legal documents, powered by LlamaIndex Index v2 (LlamaParse Platform). The project demonstrates a pattern the team calls the Retrieval Harness for agent retrieval. The method is different from single shot recovery. Instead of embedding searches per query, the agent is provided … Read more
Most business data still sits inside PDFs, scans, and slide decks. Main language models and agents cannot use that data until it is formatted JSON. The release of an open source document has become a common way to make such modifications to your hardware. Two different problems hide under the name ‘PDF to JSON.’ The … Read more