All News

1492 technical news articles

Transformers Community Proposes Sequence Isolation Fix After Missing Acceleration Packages May Change Model Outputs

A Transformers development-branch report on October 9 found that some PyTorch fallback operators ignore document boundaries, allowing packed sequences to affect one another. The community has proposed a fix and comparison tests, but the proposal has not been merged, and the impact on released versions remains to be confirmed.

2026-10-09

GitHub Repo

Langflow Community Reports Prompt Caching Gap: Second-Level Timestamps May Block Reuse of Multi-Turn Conversation History

A Langflow community report on October 9 says a date field in the Agent’s default prompt injects a second-level timestamp on every run, which may prevent later turns from hitting the prompt cache. The report suggests using a date instead, but public performance measurements and verification of an official fix are still lacking.

2026-10-10

Microsoft Releases Microsoft-Decision-1, Scoring Option Probabilities for Agent Workflows in a Single Inference

Microsoft launched Microsoft-Decision-1 on October 9. Post-trained from Qwen3.5-9B, it returns probabilities for predefined options in classification, routing, and agent action evaluation. The model is listed on Foundry and OpenRouter, but its performance and confidence calibration still need validation against real workloads.

2026-10-10

GitHub Repo

Open WebUI Community Proposes MCP Citation Field Mapping to Reduce Retrieval Services’ Dependence on the Events API

On October 8, the Open WebUI community proposed an administrator-configured MCP citation mapping that would generate source markers directly from existing retrieval results. The project’s response noted that the Events API already supports citations; the new approach remains a partial prototype and is not yet an official feature.

2026-10-10

GitHub Repo

Firecrawl Community Reports Image-Cleanup Bug That May Delete Text and Misalign Table Columns

A Firecrawl community report filed on October 8 says the default Base64 image cleanup may cross image boundaries, removing nearby text and table cells. The report includes a minimal reproduction in a self-hosted environment and a suggested fix, but the impact on released versions and the cloud service remains unconfirmed.

2026-10-10

GitHub Repo

PyTorch Community Tracks XPU Compilation Optimization Gap: reduce-overhead Still Lacks Graph Replay

An October 10 PyTorch development-build report says reduce-overhead mode on Intel XPU does not enable the expected graph capture and replay. Official documentation still limits this optimization to CUDA; XPU integration and performance validation remain outstanding.

2026-10-10

GitHub Repo

Hermes Agent Patches Native Login Redirect Vulnerability; URL Parsing Differences Could Lead to Session Takeover

Tenable disclosed a Hermes Agent native login vulnerability on October 9: differences in how the server and browser parse callback URLs could allow authorization codes to be sent to an attacker. The fix is included in v0.21.6, but the Desktop, Termux, and Microsoft Store packages were not updated alongside this release.

2026-10-10

GitHub Repo

Ollama v0.40.2 Fixes Duplicate Model Entries and Clarifies GGUF Migration and Downgrade Backups

Ollama released v0.40.2 on October 8, fixing duplicate entries in the model list after migration of older models. Migration retains the original GGUF files to support downgrades, so engineering teams should account for disk usage and the need to re-download models if backups are deleted.

2026-10-10

GitHub Repo

PyTorch Community Reports Abnormal Attention Gradients on B300; Certain Short Sequences May Produce NaNs in cuDNN

A PyTorch community report on October 9 says that a combination of certain short sequences and Boolean masks on B300 may cause NaNs during cuDNN attention backpropagation, even though forward outputs remain normal. Maintainers said the issue did not reproduce with newer cuDNN and recommended testing a nightly build or 2.15 release candidate; the reporter’s environment has yet to be upgraded and verified.

2026-09-22

GitHub Repo

AutoGPT Platform v0.8.3 Changes Agent Approval: Sandbox Commands Judged by Supervisor Model

AutoGPT released Platform beta v0.8.3 on October 8, changing Ask First mode so a supervisor model reviews sandbox commands instead of prompting for each one. The update adds checks of script contents and shell login files, but coverage remains limited for indirect execution and file changes made after inspection.

2026-10-09

GitHub Repo

Ollama Community Proposes Gemma 4 Tool-Reply Fix for Possible Blank Answers When Thinking Is Disabled

An October 8 report from the Ollama community says Gemma 4 may generate only control tokens and then stop after receiving tool results with thinking disabled, causing the API to return a blank message. The proposed fix includes renderer tests, but the full failure case has not been publicly reproduced and the patch has not been merged.

2026-10-10

GitHub Repo

LangChain Core 1.6.8 Strengthens IPv6 SSRF Checks, Adds Interface Scope and Embedded IPv4 Handling

LangChain released Core 1.6.8 on October 8, updating IPv6 address normalization and embedded IPv4 checks to strengthen blocking of local and cloud metadata endpoints. The fix has been merged and published on PyPI, but automated review also flagged possible changes to some default blocking behavior, so engineering teams should verify their custom network-range rules.

2026-10-09