PulseAugur
中
实时 18:03:14
English(EN) Eval-Driven Development for a .NET Agent: Replaying Traces Instead of Re-Calling the Model

Ollama 添加 Recursive 的 Flint 模型；.NET 智能体开发使用追踪记录重放

作者 PulseAugur 编辑部 · [2 个来源] ·

新版 Ollama v0.40.8 已发布，增加了对 Flint 模型（Recursive 开发的拥有 400 亿参数的混合专家编码模型，具有 262K 标记上下文窗口）的支持。此次更新还包括对 macOS 上 Flint 的初步支持，未来版本计划提供更广泛的 GPU 支持。此外，一项独立开发工作通过 .NET 实现的评估驱动开发，利用追踪记录重放来测试智能体行为而不重复调用模型，从而改进了 AI 智能体的评估。 AI

影响 Ollama 对 Flint 等新模型的支持扩展了开发人员对高级 AI 功能的访问，而评估驱动开发实践提高了 AI 智能体部署的可靠性和效率。

排序理由 该集群讨论了工具 (Ollama) 的软件更新和 AI 智能体的开发方法论，而不是核心 AI 模型发布或研究。

在 Towards AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Ollama 添加 Recursive 的 Flint 模型；.NET 智能体开发使用追踪记录重放

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群讨论了工具 (Ollama) 的软件更新和 AI 智能体的开发方法论，而不是核心 AI 模型发布或研究。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. Towards AI TIER_1 English(EN) · Ali Süleyman TOPUZ ·

    Eval-Driven Development for a .NET Agent: Replaying Traces Instead of Re-Calling the Model

    <h4><em>How I ported a Python eval-driven setup to C#, why my LLM judge gave a dangerous answer a perfect score, and what I changed in the rubric afterwards.</em></h4><p>The moment I decided to take evals on my .NET agent seriously was not dramatic. I changed one sentence in a sy…

  2. Mastodon — mastodon.social TIER_1 English(EN) · whatsnew_fyi ·

    Ollama v0.40.8 Support for the Flint model from Recursive, a 40B-parameter mixture-of-experts coding model with a 262K-token context window, available via ollam

    Ollama v0.40.8 Support for the Flint model from Recursive, a 40B-parameter mixture-of-experts coding model with a 262K-token context window, available via ollama run flint; Flint is supported on MacOS; other GPU support will be enabled in a subsequent release https:// whatsnew.fy…

相关实体

相关话题