Archive
1492 technical news articles
GitHub Repo
LangGraph maintainers published a security advisory on October 7, reporting that the JS SDK modifies caller-provided header objects, which may cause clients to share credentials. The advisory lists patched versions, but the issue requires a specific shared-object configuration to trigger and is rated low risk.
最新模型
Anthropic released Claude Haiku 5.5 on October 7, with adjustable reasoning effort and lower per-token prices for short prompts. AWS is offering the model as well, but long-prompt pricing, cross-region routing, and the cost of real-world tasks still need separate evaluation.
GitHub Repo
A community reproduction on October 6 found that importing a Gemma 4 12B GGUF into Ollama under a name without its size may trigger the wrong prompt template. A proposed fix includes a regression test but has not been merged, and its effect on generation quality remains unmeasured.
GitHub Repo
An Open WebUI community report dated October 6 says the knowledge-base workflow may read from Qdrant before a batch write finishes, leaving an incomplete copy of a document. The report includes version details, logs, and a verification method, but no maintainer confirmation or merged fix has been reported.
GitHub Repo
A reproduction on the October 7 development build suggests that appending multiple tokens after reusing a prefix may leave more than the configured threshold in the full-precision cache. The report includes a test that requires no weight downloads, but maintainers have not confirmed the issue, and GPU memory and output-quality effects have not been verified.
最新模型
On October 7, Liquid AI released d1-3B and the experimental d1-omni-600M, which return structured decisions without generating answers token by token. Local and Jetson deployment examples are available, but the low-latency figures depend on warm-up conditions, and evaluation results are still primarily based on the company’s own testing.
最新模型
On October 6, Google released EmbeddingGemma 2, which maps text, code, images, video, and audio into a shared vector space and makes its weights available under Apache 2.0. The model can load encoders as needed, but quantized memory figures and full-precision evaluation results should be interpreted separately.
GitHub Repo
A PyTorch 2.14 CPU community reproduction on October 6 found that rounding in intermediate logit calculations may cause about 50% relative error for certain half-precision inputs. The report includes an exhaustive enumeration of inputs and proposed patch code, but the patch has not been validated in an actual build.
GitHub Repo
An October 7 Ollama community test found higher latency for long-prompt requests with three decision models using MLX quantized formats on M5 Pro than with BF16. The report includes measurement methods and reproduction instructions, but maintainers have yet to confirm whether dequantization is a bottleneck.
GitHub Repo
A development-build reproduction reported on October 6 suggests that switching T5’s attention backend after loading may update only the top-level setting, while the encoder and decoder continue using eager. The report includes direct call counts, but maintainers have not confirmed the issue and no fix has been merged.
GitHub Repo
A community reproduction on October 5 using Langflow 1.12.4 indicates that concurrent workflows running in the same process may send LangChain trace records to the first Phoenix project. The report includes a minimal reproduction and output comparison, but maintainers have not confirmed the issue and no fix has been merged.
GitHub Repo
A community report dated October 6 says image requests to Qwen3-VL may repeatedly crash the inference process when another large model is already using both GPUs. The report includes a core-dump stack trace, but maintainers have yet to confirm whether memory pressure caused a null-pointer error.