Smollm3: Smol, multilingual, long-context reasoner LLM
(news.ycombinator.com)
421.
422.
Bosses Are Using AI to Decide Who to Fire
(futurism.com)
423.
Optimizing Tool Selection for LLM Workflows with Differentiable Programming
(news.ycombinator.com)
424.
VLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention
(news.ycombinator.com)
425.
Tools: Code Is All You Need
(news.ycombinator.com)
426.
Writing Code Was Never the Bottleneck
(news.ycombinator.com)
427.
LLMs as Compilers
(news.ycombinator.com)
428.
What to build instead of AI agents
(news.ycombinator.com)
429.
Slouching Towards Sensemaking
(news.ycombinator.com)
430.
Life of an inference request (vLLM V1): How LLMs are served efficiently at scale
(news.ycombinator.com)
431.
Lossless LLM 3x Throughput Increase by LMCache
(news.ycombinator.com)
432.
Show HN: Shouldiuse.dev – Software dependency health checker
(news.ycombinator.com)
433.
Structured Output with LangChain and Llamafile
(news.ycombinator.com)
435.
Libraries are under-used. LLMs make this problem worse
(news.ycombinator.com)
436.
437.
Brain activity much lower when using AI chatbots, MIT boffins find
(news.ycombinator.com)
438.
From LLM to AI Agent: What's the Real Journey Behind AI System Development?
(news.ycombinator.com)
439.
Yes I Will Read Ulysses Yes
(news.ycombinator.com)
440.
Building Effective AI Agents
(news.ycombinator.com)
441.
442.
Salesforce study finds LLM agents flunk CRM and confidentiality tests
(news.ycombinator.com)
443.
444.
445.
Mel Brooks is returning for Spaceballs 2
(theverge.com)
446.
Design Patterns for Securing LLM Agents Against Prompt Injections
(news.ycombinator.com)
447.
448.
Zero-click AI data leak flaw uncovered in Microsoft 365 Copilot
(bleepingcomputer.com)
449.
Launch HN: Confident AI (YC W25) – Open-source evaluation framework for LLM apps
(news.ycombinator.com)
450.
Integrating LLMs into security operations using Wazuh
(bleepingcomputer.com)