embeddings - Page 16
Stories from embeddings come first, newest first, then stories from connected topics (retrieval, RAG, open weights, AI Models, Hugging Face, AI), each labelled with where it comes from. This view is not indexed by search engines.
Latest
Underdog’s Saluki 27B Shrinks Qwen3.8-27B to 7.89 GB: Tool Calling Up on Its Own Test, Competition Maths Down
Underdog's Saluki 27B is a 7.89 GB, 2-bit version of Qwen3.8-27B. Underdog says it passes more tool-calling tasks than the full model on its own 120-task test but scores 15 to 18% lower on competition maths. What quantisation means, and what the numbers do not prove.
Firmus Pulls Its ASX IPO as Isomorphic Labs Eyes a $40bn Valuation
Three AI business items from 8–9 October 2026: Nvidia-backed Firmus withdraws its ASX listing and turns to private money; Bloomberg reports Isomorphic Labs is in early funding talks at a valuation of at least $40 billion; and StepFun's Step 5 Preview model is now listed on OpenRouter and Vercel's AI Gateway. What is confirmed, and what is only reported.
Harness Buys Augment Code Assets, Plus TRL 1.15 and Genkit Dart 1.0
Four AI developer-tool updates from 8–9 October 2026: Harness buys selected Augment Code assets (not the whole company, price undisclosed), Hugging Face's TRL v1.15.0 claims up to 6.9× longer training sequences, Google's Genkit Dart reaches 1.0, and NVIDIA shows its Boro kernel-review tool. What each says, and what it doesn't.
Two Open Models From 8 October: a Fast Coding Agent and a Gene Finder
JetBrains has released Mellum2.1, a small open model for coding agents, and Hugging Face has released Carbon-A, a 1.2B-parameter model that predicts protein-coding regions in DNA, plus a database of 566 million predicted loci. What each does, and which numbers are the developers' own.
Same Model, Different Score: Training AI Inside the Coding Tools People Actually Use
Hugging Face's FineEnvs team has released an open framework that turns unmodified coding-agent harnesses such as Claude Code, Codex and OpenCode into reinforcement-learning environments. In its own tests, one small model scored 62% in one harness and 33% in another. What a harness is, how the training works, and what the results do and do not show.
OpenAI’s Decisions API and Perplexity’s Decider Return Probabilities
On 6 October OpenAI launched a Decisions API that returns yes/no probabilities, picks and rubric scores from GPT-6 Luna, and cut its API usage tiers from five to three. Perplexity released pplx-decider-v1.1-27b, an Apache 2.0 open-weight decision model. What decision models are, what each costs, and which scores are the vendors' own.
RAG vs Jev+RAG Explained: What the Judgment Gate Adds
Avi Chawla’s 7 October explainer contrasts standard RAG with a Jev gate between retrieval and generation. What hybrid search already does, what typed probabilities add, why thresholds stay in code, and what this architecture does not replace.
Google’s EmbeddingGemma 2 Puts Open Multimodal Embeddings on Phones
Google DeepMind released EmbeddingGemma 2 on 6 October 2026: a 740M Apache 2.0 multimodal embedding model for on-device text, image, audio and video retrieval.
Reflection’s Beam: an open-weight workhorse pitched on efficiency
Reflection AI introduced Beam, a sparse open-weight Mixture-of-Experts model with 501 billion total parameters and 23 billion active, aimed at coding and agentic work. Weights are promised later this month; scores are company-reported.
Personalised RAG, Memory and AI Agents: How a Hybrid Assistant Works
Update, 2 Nov 2026: This explainer has been revised. We removed an unsupported claim about measured gains from chatbot memory features, softened claims that RAG systems do...
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.