Feed aggregator

Article URL: https://driftspeed.wordpress.com/2026/08/07/ai-on-a-piece-of-sponge/

Comments URL: https://news.ycombinator.com/item?id=49218810

Points: 1

# Comments: 1

Article URL: https://thezvi.substack.com/p/openai-trained-its-models-for-months

Comments URL: https://news.ycombinator.com/item?id=49218776

Points: 2

# Comments: 0

Article URL: https://etherpad.org/

Comments URL: https://news.ycombinator.com/item?id=49218747

Points: 3

# Comments: 0

Article URL: https://www.quantamagazine.org/neutrinos-from-deep-inside-earth-provide-a-new-picture-of-the-mantle-20260807/

Comments URL: https://news.ycombinator.com/item?id=49218745

Points: 1

# Comments: 0

Article URL: https://www.labormarketmatters.com/p/mr-balaji-goes-to-kazakhstan

Comments URL: https://news.ycombinator.com/item?id=49218727

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2026/08/05/nyregion/new-school-faculty-fired-nyc.html

Comments URL: https://news.ycombinator.com/item?id=49218723

Points: 1

# Comments: 0

Article URL: https://web.archive.org/web/20260731053721/http://github.com/ancaferro/myNetwork/pull/3

Comments URL: https://news.ycombinator.com/item?id=49218707

Points: 21

# Comments: 7

Article URL: https://secsift.com

Comments URL: https://news.ycombinator.com/item?id=49218695

Points: 1

# Comments: 0

Article URL: https://play.google.com/store/apps/details?id=com.utter.app&hl=en_US

Comments URL: https://news.ycombinator.com/item?id=49218691

Points: 1

# Comments: 1

Article URL: https://pilgrima.ge/p/full-price

Comments URL: https://news.ycombinator.com/item?id=49218686

Points: 2

# Comments: 1

Article URL: https://sourcelibrary.org

Comments URL: https://news.ycombinator.com/item?id=49218514

Points: 1

# Comments: 0

Article URL: https://sackfield.substack.com/p/wrangling-evals

Comments URL: https://news.ycombinator.com/item?id=49218468

Points: 1

# Comments: 0

I'm really no expert and attempting to come up to speed. But...

It strikes me that LLM's are a subtle combination of knowing the language and knowing some facts. If one were making a chatbot for helping (say) people understand their tax returns then you'd want a 'base' LLM that understood language and then add domain specific knowledge via RAG. So "yes" to knowing that Thursday comes after Wednesday; "no" to knowing how high Everest is; and questions regarding income tax have to reference the RAG. Is this correct?

So are there stock "thin" models for doing this? Is it better to train your own?

Comments URL: https://news.ycombinator.com/item?id=49218466

Points: 1

# Comments: 2

Article URL: https://momath.org/the-hat/

Comments URL: https://news.ycombinator.com/item?id=49218463

Points: 1

# Comments: 0

Article URL: https://github.com/chenxiaolong/BasicSync

Comments URL: https://news.ycombinator.com/item?id=49218439

Points: 1

# Comments: 0

Article URL: https://framewrite.cc/

Comments URL: https://news.ycombinator.com/item?id=49218437

Points: 1

# Comments: 0

Article URL: https://github.com/h4ckf0r0day/obscura

Comments URL: https://news.ycombinator.com/item?id=49218432

Points: 1

# Comments: 0

Article URL: https://github.com/olafurbergs/krowser

Comments URL: https://news.ycombinator.com/item?id=49218415

Points: 1

# Comments: 0

Article URL: https://castform.com/blog/unslop/

Comments URL: https://news.ycombinator.com/item?id=49218397

Points: 1

# Comments: 0

Article URL: https://www.theguardian.com/commentisfree/2026/aug/07/trump-scientific-research-universities

Comments URL: https://news.ycombinator.com/item?id=49218390

Points: 8

# Comments: 0