Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
TypeSafe released AnyFilter, an MIT-licensed Chrome extension that uses the Jev model to hide unwanted content on any site, starting with X. Users install the extension via a Chrome zip from GitHub Releases, paste a Jev …
Vercel released Jev Playground, a browser-based tool from typesafe-ai/jev that runs on the Vercel AI Gateway and answers text, JSON, questions, Boolean, Choice, and Score prompts in a single parallel pass using a 32K-tok…
UC Berkeley researchers and the NVIDIA robotics team have developed Agentic Robotics (AR), an approach that uses multi-agent AI systems to write, test, and iteratively improve modular robot programs largely offline rathe…
Celeris announced it is building large language models around diffusion rather than autoregressive decoding, aiming to maximize useful intelligence delivered per unit of time. The company cited an NVIDIA-led study, Fast-…
A developer's teardown of the command-code CLI npm package version 1.58.0 shows that its advertised "taste-1" meta neuro-symbolic AI model is not a trained model at all: the tool shells out to git to collect up to 200 co…
Anthropic said its Claude model now leads 26% of the company's model research and development, completing most tasks end-to-end from a high-level prompt under human supervision, as leading AI labs say the industry is nea…
A developer has documented a failure mode in persistent-memory AI agents called self-reinforcing memory loops, in which an agent's own inference is stored as memory, later retrieved as evidence, and used to justify progr…
TypeSafe AI launched Jev in early access on September 15, 2026, a text-only "System One" model that takes state plus typed questions and returns bounded probabilistic decisions rather than generated text. According to a …
A developer detailed a method for connecting the DEVUP AI platform to Visual Studio Code using VS Code's native Custom Endpoint provider, introduced in stable version 1.122, without installing any extension. The setup re…
Fatih Kadir Akın created f/prompts.chat, described as the first git-native repository for system prompt primitives, following ChatGPT's arrival in late 2022. The project frames persona definitions as deterministic instru…
A developer documented building an AI agent pipeline to automate real estate comparable-sales analysis, using LangGraph and CrewAI to structure data retrieval, filtering, adjustment calculation, and report generation. Th…
A developer has published a technical explainer on tokenization, detailing how large language models convert text into integer token sequences rather than processing words directly. The writeup covers subword tokenizatio…
A practical guide explains how large language models work for product managers without requiring deep ML expertise, walking through the pipeline from tokenization and embeddings through the Transformer's self-attention a…
Cooley deployed a custom system called GO Public built on ChatGPT to identify legal and compliance risks earlier in the IPO preparation process, according to OpenAI. The system scopes AI to early-stage issue spotting rat…
Anthropic released Claude Fable 5.1 on September 1, cutting the cache-read price 75% from $1.00 to $0.25 per million tokens while leaving input at $10 and output at $50 per million tokens unchanged. The discount applies …
University of Tartu Professor of Artificial Intelligence Meelis Kull said there is no existential risk from today's chatbots, stating the threat from current AI capabilities is "close to zero." Kull's assessment contrast…
A developer has released Bonsai, a 27-billion-parameter reasoning model designed to run on a 16 GB M2 Mac, alongside a companion tool called Ferrox. The project targets local inference of a large reasoning model on consu…
Cornell University researchers found that the names and occupations Elias, Mara, Elara, lighthouse keeper, clockmaker, and librarian appeared in 88 percent of roughly 20,000 AI-generated stories tested across models from…
A developer built an open-source tool called judgeDjudge to evaluate LLM-as-a-judge systems, testing judges for repeated-run consistency, position bias, sensitivity to verbosity, and accuracy in preferring the better res…
A user improved the agentic coding performance of Ternary Bonsai 2, a Qwen 3.8 27B-based model, when run locally through llama-cpp by switching its thinking setting from "xhigh" to medium via the chat-template-kwargs arg…