Feed aggregator

Article URL: https://www.easelinktech.com/not-all-on-device-ai-is-the-same-how-chip-compute-tiers-decide-what-your-product-can-actually-do/

Comments URL: https://news.ycombinator.com/item?id=48266512

Points: 1

# Comments: 0

Article URL: https://www.msuiche.com/posts/supply-chain-attacks-cluster-230000-advisories-five-patterns/

Comments URL: https://news.ycombinator.com/item?id=48266511

Points: 1

# Comments: 0

Article URL: https://aliyev.site/rcf/

Comments URL: https://news.ycombinator.com/item?id=48266509

Points: 2

# Comments: 1

Article URL: https://news.onbrn.com/migrating-from-github-actions-to-sourcehut-builds/

Comments URL: https://news.ycombinator.com/item?id=48266506

Points: 2

# Comments: 0

Article URL: https://lean-lang.org/

Comments URL: https://news.ycombinator.com/item?id=48266500

Points: 1

# Comments: 0

Article URL: https://religionnews.com/2026/05/25/in-his-first-encyclical-pope-leo-xiv-says-ai-must-serve-humanity-not-the-powerful-few/

Comments URL: https://news.ycombinator.com/item?id=48266485

Points: 6

# Comments: 0

Article URL: https://jimmyhmiller.com/legibility-is-ruining-you

Comments URL: https://news.ycombinator.com/item?id=48266465

Points: 1

# Comments: 0

Article URL: https://birdclaw.sh/

Comments URL: https://news.ycombinator.com/item?id=48266104

Points: 1

# Comments: 0

Article URL: https://hawksley.org/2026/01/14/beyond-senior.html

Comments URL: https://news.ycombinator.com/item?id=48266103

Points: 1

# Comments: 0

Article URL: https://fedemagnani.github.io/math/2025/07/04/fenchel.html

Comments URL: https://news.ycombinator.com/item?id=48266095

Points: 1

# Comments: 0

Article URL: https://lab5.ca/blog/spec-driven-development/

Comments URL: https://news.ycombinator.com/item?id=48266085

Points: 1

# Comments: 0

Article URL: https://github.com/sindresorhus/awesome

Comments URL: https://news.ycombinator.com/item?id=48266077

Points: 1

# Comments: 0

Article URL: https://autolang.vercel.app/docs/philosophy-vision

Comments URL: https://news.ycombinator.com/item?id=48266073

Points: 1

# Comments: 0

Article URL: https://www.core77.com/posts/143823/Nendos-Wonderful-Toru-an-Electric-Kettle-for-Alessi

Comments URL: https://news.ycombinator.com/item?id=48266067

Points: 1

# Comments: 0

Article URL: https://techcrunch.com/2026/05/21/six-search-engines-worth-trying-now-that-google-isnt-really-google-anymore/

Comments URL: https://news.ycombinator.com/item?id=48266051

Points: 2

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Towel_Day

Comments URL: https://news.ycombinator.com/item?id=48266009

Points: 1

# Comments: 0

Article URL: https://zhuohangu.github.io/blog-post-peek/

Comments URL: https://news.ycombinator.com/item?id=48266008

Points: 2

# Comments: 0

What are your experiences with all the different variations of finetunes on small models (<40B) with those popular datasets? My personal experience is mostly with the 'Opus-Reasoning' ones on qwen models, and aside from the output being subjectively better looking (ascii charts and all), in actual coding performance every one I've tried tends to become a lot more overconfident, writing more messy and buggy code and tries to gaslight me that the task I give it is impossible when it cannot achieve it.

I have seen them perform better on public benchmarks in some cases, which shouldn't be ignored completely, but that doesn't seem to translate to better output on real work in my limited testing.

What are your observations? Any specific ones that you lean towards, or have had good experiences with?

Comments URL: https://news.ycombinator.com/item?id=48266001

Points: 1

# Comments: 0

Article URL: https://agent-data.dev/blog/benchmarking-ai-agent-web-access/

Comments URL: https://news.ycombinator.com/item?id=48265995

Points: 2

# Comments: 0

Article URL: https://atomsfrontier.substack.com/p/velocity-in-every-voxel

Comments URL: https://news.ycombinator.com/item?id=48265989

Points: 1

# Comments: 0