Channels

Public threads, grouped by where they are happening. Pick a place to read its topics.

llm

Filed under this by 22 pieces from 2 sources · the whole ledger

  1. Eval-driven development: Lessons from evaluating GenAI at scalemedium.comstory
  2. Using AI to find patient zero in marketing campaignssimplecast.comaudio
  3. Improving on a 30-year-old hardware architecturesimplecast.comaudio
  4. “Translation is the tip of the iceberg”: A deep dive into specialty modelssimplecast.comaudio
  5. Writing tests with AI, but not LLMssimplecast.comaudio
  6. “Data is the key”: Twilio’s Head of R&D on the need for good datasimplecast.comaudio
  7. Your docs are your infrastructuresimplecast.comaudio
  8. A student of Geoff Hinton, Yann LeCun, and Jeff Dean explains where AI is headedsimplecast.comaudio
  9. One of the world’s biggest web scrapers has some thoughts on data ownershipsimplecast.comaudio
  10. How to detect errors in AI-generated codesimplecast.comaudio
  11. The framework helping devs build LLM appssimplecast.comaudio
  12. We chat search from both sides nowsimplecast.comaudio
  13. Is GenAI the next dot-com bubble?simplecast.comaudio
  14. Diverting more backdoor disasterssimplecast.comaudio
  15. Are long context windows the end of RAG?simplecast.comaudio
  16. Your whole repo fits in the context windowsimplecast.comaudio
  17. How Stack Overflow is partnering with Google to encourage socially responsible AIsimplecast.comaudio
  18. A leading ML educator on what you need to know about LLMssimplecast.comaudio
  19. It’s RAG time for LLMs that need a source of truthsimplecast.comaudio
  20. What Gemini means for the GenAI boomsimplecast.comaudio
  21. USB-C for all, PHP 4EVA, and what do LLMs actually know (if anything)?simplecast.comaudio
  22. Semantic search without the napalm grandma exploitsimplecast.comaudio

A topic here is a label each publisher printed on its own piece. Equal labels from different publishers are shown together; that does not make them one subject.

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

Where this comes from

Solid branches are exact SourceFrontier census edges used by this page. Folded branches share the publisher but did not supply these items.

Hacker News

1 feed · 1 available · hn.algolia.com

text1 channel · 1 available
  1. Used here by hn-new hacker-attention Hacker News
    used on this pagehacker-attention

Latest

It's enough - vibecoding tag crossed from useless to harmfulThe vibecoding tag has been getting more and more useless for a while now. It lost the original meaning as the culture of software engineering with LLMs matured a bit. It got silly when posts talking about LLMs in general got tagged. It got useless when posts even mentioning some project created with LLMs in passing got tagged. Now it actually got harmful to the community when tagging posts turns away very valuable members https://lobste.rs/c/vecuxj I sighed and moved on for a while now as almost everything gets tagged - you can skip a word. But now it not only carries no signal whatsoever, it turns away people creating original technical content - which is what I assume anti-vibecoding people would actually like to see more of. Please split it or kill it. But we'd be better off without what exists today. Added: To be clear, I totally support people filtering out llm-generated or llm-centric posts. But right now everyone loses. And every day we lose a little bit more. Whether it's an original, interesting arviraptor lobste.rs