1
What is the status on continual learning for LLMs?
持续学习若解决，AGI近在咫尺，来看看社区对此现状的讨论
I belive if this is solved, agi is very close. So id like to know if its solvable Comments URL: https://news.ycombinator.com/item?id=49050360 Points: …
2
Ask HN: How do we measure software in LLM era?
面对LLM时代的软件度量困境，该帖引发关于准确性、成本、上下文等多维度指标如何平衡的深度思考
A bit of a rant. Sorry! With the probablistic pluggable 'brain' existing in parts of the solution how are you measuring anything is better or worse? I…
3
Show HN: Chess in SQL
用纯SQL实现可下棋的国际象棋引擎，挑战数据库与函数式编程的极限。
Article URL: https://swingbit.github.io/quackmate/ Comments URL: https://news.ycombinator.com/item?id=48525459 Points: 2 # Comments: 0
4
Ask HN: Why is it still so hard for LLMs to query NoSQL databases?
LLM处理SQL得心应手，但面对NoSQL数据库却屡屡碰壁，根源在于其查询模型的碎片化与多样性。
LLMs are good at SQL. It's precise, expressive, and unambiguous. If you connect an MCP server to Postgres, then the agent can query it directly. The s…
5
A narrowing window to understand AI
AI理解窗口正在缩小，揭示技术黑箱化带来的紧迫挑战
Article URL: https://www.science.org/doi/10.1126/science.aei3167 Comments URL: https://news.ycombinator.com/item?id=48403290 Points: 2 # Comments: 0
6
Train your own LLM? Here's what happens
从零训练一个大语言模型有多难？作者分享端到端构建LLM的真实过程与关键教训。
Article URL: https://www.exasol.com/blog/train-your-own-llm/ Comments URL: https://news.ycombinator.com/item?id=48396068 Points: 7 # Comments: 0