←Search results

Search “Reasoning”

By relevance · Total 3280 results Clear search

Friday

Thursday

  5. A6 a6-051 · Cerebras：Blog

    Cerebras Partners with Armis: Using Ultra-Fast AI to Accelerate Application Security Vulnerability Remediation

    Cerebras and Armis have announced a partnership that combines Armis Centrix™ for Application Security with Cerebras' ultra-fast AI inference capabilities to help teams identify and remediate vulnerabilities faster. Armis launched this AI-driven application security platform on February 10, 2026; it can scan code, dependencies, container images, and configuration files, and the company says it achieved the highest performance in the third-party Public CASTLE Benchmark C@250.

    Matched fieldsSummary、Body

    #a6-editorial#Industry news#English text is being prepared.#Safety / alignment
  7. A6 a6-051 · Cerebras：Blog

    Cerebras: Latency Debt Is Dragging Down AI Experience, GPUs Have Hit a Bottleneck

    Cerebras proposes the concept of "latency debt": model parameters have grown from 340M in BERT-Large to over 1T in Kimi-k2, the share of inference tokens has risen from under 10% to over 50%, context has expanded from about 1,000 tokens in GPT-2 to 10 million tokens, input length has doubled every year and output has tripled, causing latency to accumulate continuously. Cerebras says its Wafer-Scale Engine (WSE) keeps data on-chip, eliminating the memory bandwidth bottleneck of GPU inference, and OpenAI has already purchased 750 MW of compute from it.

    Cerebras proposes the concept of "latency debt": model parameters have grown from 340M in BERT-Large to over 1T in Kimi-k2, the share of inference tokens has risen from under 10% to over 50%, context has expanded from about 1,000 tokens in GPT-2 to 10 million tokens, input length has doubled every year and output has tripled, causing latency to accumulate continuously. Cerebras says its Wafer-Scale Engine (WSE) keeps data on-chip, eliminating the memory bandwidth bottleneck of GPU inference, and

    Matched fieldsSummary、Body

    #a6-editorial#Industry news#English text is being prepared.#Reasoning
  9. A6 a6-051 · Cerebras：Blog

    How Cerebras Keeps Autoresearch Loops From Going Off Track: Lessons From 71 Experiments

    Cerebras had an AI agent run 71 experiments across two task types—training optimization and model compression—and found that when the loop scope is tightened, it reliably produces real conclusions, while once the guardrails are loosened, the agent drifts from the goal within hours. In experiment one, codex-autoresearch-harness was used to wrap Codex in a bash loop; GPT-5.4 and Codex-Spark each independently converged on a learning-rate warmdown schedule within 6 hours, but GPT-5.4 had a proposal acceptance rate of 67% versus only 17% for Spark, showing that proposal quality determines total cost more than single-inference speed. In experiment two, REAP plus INT4 quantization compressed a 717 GB model to 92 GB, with dynamic expert swap-in/swap-out taking 0.151 seconds, but after 12 hours of unattended operation the agent changed to asking a different question on its own; the authors corrected this by clearing context, isolating directories, and adding more frequent validation checkpoints.

    Cerebras had an AI agent run 71 experiments across two task types—training optimization and model compression—and found that when the loop scope is tightened, it reliably produces real conclusions, while once the guardrails are loosened, the agent drifts from the goal within hours. In experiment one, codex-autoresearch-harness was used to wrap Codex in a bash loop; GPT-5.4 and Codex-Spark each independently converged on a learning-rate warmdown schedule within 6 hours, but GPT-5.4 had a proposal

    Matched fieldsSummary、Body

    #a6-editorial#Tutorials / practice#Agents#English text is being prepared.
  11. A6 a6-047 · Baseten Engineering Blog

    Baseten Engineering Blog: A Roundup of Model Performance Optimization Practices

    The model performance section of the Baseten engineering blog rounds up several inference optimization efforts, including speeding up pyannote's speaker diarization model by 9.6x, speeding up Kimi K3 tokenization by 18x under million-token agent workloads, and performing inference engineering optimization for DeepSeek V4 Pro 0813. The section also covers delta weight synchronization optimization for hosted RL rollouts, Coval voice AI benchmarking, and the practice of building APIs for Kimi K3 and GLM-5.2.

    The model performance section of the Baseten engineering blog rounds up several inference optimization efforts, including speeding up pyannote's speaker diarization model by 9.6x, speeding up Kimi K3 tokenization by 18x under million-token agent workloads, and performing inference engineering optimization for DeepSeek V4 Pro 0813. The section also covers delta weight synchronization optimization for hosted RL rollouts, Coval voice AI benchmarking, and the practice of building APIs for Kimi K3 an

    Matched fieldsSummary、Body

    #a6-editorial#Industry news#English text is being prepared.
  12. A6 a6-047 · Baseten Engineering Blog

    Baseten Engineering Blog AI Models Article List

    The AI Models section of the Baseten Engineering Blog brings together multiple articles on models and inference engineering, including NVIDIA Nemotron 3 Diarization, which achieves real-time speaker labeling at one cent per audio hour; DeepSeek-V4.1-Flash, which offers more efficient prefill for coding agents; and introductions to new models such as NVIDIA Nemotron 3.5 Lightning, Nemotron 3.5 ASR Streaming, and Nemotron 3 Embed. It also covers topics such as GLM-5.3 post-training scaling, GLM 5.2 vision capabilities, Laguna S 2.1, and recommendations for open-source post-trained models.

    The AI Models section of the Baseten Engineering Blog brings together multiple articles on models and inference engineering, including NVIDIA Nemotron 3 Diarization, which achieves real-time speaker labeling at one cent per audio hour; DeepSeek-V4.1-Flash, which offers more efficient prefill for coding agents; and introductions to new models such as NVIDIA Nemotron 3.5 Lightning, Nemotron 3.5 ASR Streaming, and Nemotron 3 Embed. It also covers topics such as GLM-5.3 post-training scaling, GLM 5.

    Matched fieldsSummary、Body

    #a6-editorial#English text is being prepared.
  13. A6 a6-047 · Baseten Engineering Blog

    List of Baseten Engineering Blog Infrastructure Articles

    The Baseten Engineering Blog infrastructure section aggregates multiple articles, covering topics such as LLM inference observability, a comparison of H100, H200, and B200 GPUs, building RBAC for enterprises, accelerating cold starts with the Baseten Delivery Network (BDN), running AI video on Nebius, and delivering healthcare GenAI solutions in partnership with Vultr.

    Matched fieldsSummary、Body

    #a6-editorial#English text is being prepared.
  14. A6 a6-047 · Baseten Engineering Blog

    Baseten Engineering Blog Community Articles Roundup

    The Baseten Engineering Blog Community section brings together multiple articles, covering topics such as open-source inference for You.com, AI model selection lessons from Notion and Gamma, inference in the era of continual learning, model fine-tuning and a conversation with Hollywood, the Baseten inference stack at NVIDIA Dynamo Day, and building agents on Baseten with LangChain Agent Builder + GLM 4.7.

    Matched fieldsSummary、Body

    #a6-editorial#English text is being prepared.

Wednesday