20:361 Oct UTC
pplx-decider-v1-27b
pplx-decider-v1-27b is a decision model fine-tuned from Qwen3.8-27B. It supports text classification and can also accept images for prediction.
Sources: Hugging Face
1
High confidence
Daily brief2026-10-01 UTC
AI brief · 1 October 2026
TL;DR
Models
Perplexity introduced pplx-decider-v1-27b, a text classification model fine-tuned from Qwen3.8-27B that also accepts images and provides calibrated probabilities. [1] Other releases include Qwen3.8-27B-pi for coding in the Pi agent harness; contextual embeddings for RAG; and Clef and Clef-Flash, multimodal models that return structured decisions. [2] [4] [5] [6] Video-related releases include a MiniMax H3 checkpoint for 2× video decoding and optional image detail enhancement, and a 19B model listed for use in a local Diffusers setup. [3] [7]
Developer platforms
Ai2 introduced Olmo-core 3, an open framework for developing and training large mixture-of-experts models, with a redesigned training system. [8]
Applications
GitHub added whole codebase indexing for C++ in Copilot CLI, building a persistent symbol index that is reused and dynamically updated; the feature is enabled by default. [9] GitHub's Copilot app added public-preview local sandboxing with per-project policies that limit filesystem, network and credential access for repository sessions. [10]
The records
10 developmentsEach numbered link above points to one of these catalog records, with its sources.
14:341 Oct UTC
Qwen3.8-27B-pi
Qwen3.8-27B-pi is a fine-tuned version of Qwen3.8-27B for coding work in the Pi agent harness. It is designed for iterative repository work, including editing files, running tools, and responding to feedback, with adjustable reasoning effort.
Sources: Hugging Face
1
High confidence
14:341 Oct UTC
MiniMax-H3-X2-Detail-v1
A modified MiniMax H3 VAE checkpoint with two uses: 2× video decoding and optional detail enhancement of an RGB reference image. The release includes a ComfyUI custom node and workflow, and requires a separate fast decode node for the 2× workflow.
Sources: Hugging Face
1
High confidence
02:301 Oct UTC
pplx-embed-v2-context-9b-preview
pplx-embed-v2-context-9b-preview is a contextual embedding model for document chunks in RAG systems. It encodes document chunks together so each chunk’s embedding reflects its surrounding context, and returns one embedding per chunk.
Sources: Perplexity
1
High confidence
20:361 Oct UTC
Clef-Flash
Clef-Flash is a 9B multimodal model that maps a state and a schema of typed questions to decisions. It returns a probability for each allowed option, without free-form text generation or output parsing.
Sources: Hugging Face
.88
High confidence
20:361 Oct UTC
Clef
Clef is a 27B multimodal decision model that takes a state and typed questions, then returns probabilities for each allowed option. It accepts text, JSON, images, and video, and produces structured decisions rather than free-form text.
Sources: Hugging Face
.88
High confidence
08:321 Oct UTC
SoL-Refiner-LTX-2.5-for-MiniMax-H3
SoL-Refiner-LTX-2.5-for-MiniMax-H3 is listed on Hugging Face as a 19B-parameter model in Safetensors format. The listing identifies a Diffusers pipeline but has no model card and is not deployed by an Inference Provider.
Sources: Hugging Face
.88
High confidence
20:361 Oct UTC
Olmo-core 3
Olmo-core 3 is an open framework for developing and training large mixture-of-experts models. Its redesigned training system combines distributed training techniques and routing and computation optimizations, and has been benchmarked at over one trillion total parameters.
Sources: Ai2, Hugging Face
1
High confidence
20:361 Oct UTC
Major release
Copilot CLI
Copilot CLI adds whole codebase indexing (WCI) for C++ that builds a persistent symbol index across a project so the Microsoft C++ Language Server can resolve symbols and relationships without repeatedly rediscovering them. The feature is enabled by default, can increase initial build time and memory usage, and the index is reused and dynamically updated thereafter.
Computer use is available in public preview, enabling Copilot to interact with desktop applications on the user's behalf.
1
High confidence
20:361 Oct UTC
Major release
Copilot app (Local sandboxing)
Local sandboxing for the Copilot app provides per-project policies that limit filesystem, network, and credential access for local repository and working-tree sessions. The feature is available in public preview and is configurable in the app per project or for individual sessions with an in-session command.
Computer use is available in public preview in the GitHub Copilot app on macOS and Windows, enabling Copilot to interact with desktop applications on the user's behalf.
.98
High confidence
Corrections
3Records the catalog corrected or marked withdrawn in this window. Each record page lists its versions.
06:481 Oct UTC
Correction
GPT-6 Luna
06:481 Oct UTC
Correction
GPT-6 Sol
06:481 Oct UTC
Correction
Claude Opus 5.5
Written by openai/gpt-6-luna from the catalog records listed here; every sentence cites the records it rests on. Which records a brief covers is decided by fixed rules: the new developments and major releases of the window with the strongest evidence.
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.