Feed aggregator

Article URL: https://hebbianrobotics.com/blog/youtube-system-design-for-robotics-data-infrastructure

Comments URL: https://news.ycombinator.com/item?id=48995923

Points: 1

# Comments: 0

Article URL: https://www.france24.com/en/live-news/20260721-tour-de-france-hit-by-new-wave-of-anti-doping-tests

Comments URL: https://news.ycombinator.com/item?id=48995915

Points: 1

# Comments: 0

Article URL: https://github.com/aido-dev/aido

Comments URL: https://news.ycombinator.com/item?id=48995912

Points: 1

# Comments: 0

Article URL: https://unsung.aresluna.org/try-quickly-typing-123-i-bet-you-wont-get-6/

Comments URL: https://news.ycombinator.com/item?id=48995910

Points: 1

# Comments: 0

Hi, inspired by Andrej Karpathy's autoresearch, I built autoretrieval, a small framework that lets an AI agent improve a RAG pipeline by running experiments against an evaluation dataset.

The agent edits the retrieval pipeline, runs an eval, checks whether the F-beta score improved, keeps or discards the change, and repeats. It can try different chunking strategies, chunk sizes, the number of retrieved chunks, embedding models, keyword retrieval, and more, while keeping a log of every experiment.

The repo also includes a script that generates question and reference-highlight pairs from any document collection. This makes it possible to optimize a RAG pipeline for domain-specific data.

On one of my own RAG pipelines, it more than doubled the F3 score after a few hours of running experiments.

I'd love to hear any feedback or ideas.

Comments URL: https://news.ycombinator.com/item?id=48995907

Points: 1

# Comments: 0

Article URL: https://iii.dev/blog/loops-graphs-and-the-layer-that-matters/

Comments URL: https://news.ycombinator.com/item?id=48995842

Points: 1

# Comments: 0

Article URL: https://www.zdnet.com/article/flock-ai-cameras-risks-us-how-to-find-nearby-what-they-track/

Comments URL: https://news.ycombinator.com/item?id=48995830

Points: 3

# Comments: 0

Article URL: https://mentraglass.com/blogs/blog/mentra-roadmap-update-moving-to-miniapps-on-the-phone

Comments URL: https://news.ycombinator.com/item?id=48995829

Points: 1

# Comments: 0

Article URL: https://arxiv.org/abs/2607.14656

Comments URL: https://news.ycombinator.com/item?id=48995814

Points: 2

# Comments: 0

Article URL: https://www.youtube.com/watch?v=-W2JdSl1v48

Comments URL: https://news.ycombinator.com/item?id=48995806

Points: 1

# Comments: 0

Article URL: https://support.apple.com/guide/certifications/apple-private-cloud-compute-soc-3-audit-apc95a31b9d8/web

Comments URL: https://news.ycombinator.com/item?id=48995796

Points: 1

# Comments: 0

Article URL: https://github.com/RubricLab/tokenmaxx

Comments URL: https://news.ycombinator.com/item?id=48995775

Points: 4

# Comments: 0

Article URL: https://andrewrussell.substack.com/p/i-built-an-ai-agent-i-cant-turn-

Comments URL: https://news.ycombinator.com/item?id=48995773

Points: 1

# Comments: 0

Article URL: https://clickhouse.com/blog/postgresbench-ha

Comments URL: https://news.ycombinator.com/item?id=48995768

Points: 1

# Comments: 0

Article URL: https://arxiv.org/abs/2507.09369

Comments URL: https://news.ycombinator.com/item?id=48995767

Points: 1

# Comments: 0

The open-weight Antares models are designed to pinpoint known vulnerabilities in codebases faster and at a fraction of the cost of larger AI models.

The post Cisco Launches Low-Cost AI Models for Source Code Security appeared first on SecurityWeek.

Mark Papermaster says Europe’s commitment to interoperability and diversity of supply could become a strategic advantage as AI infrastructure grows more heterogeneous

Article URL: https://worksinprogress.co/issue/how-tv-learned-to-sell-itself/

Comments URL: https://news.ycombinator.com/item?id=48995109

Points: 1

# Comments: 0

Article URL: https://prilik.com/blog/post/automating-ac-nyc/

Comments URL: https://news.ycombinator.com/item?id=48995104

Points: 1

# Comments: 0