Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
61.
Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio (news.ycombinator.com)
62.
57% of enterprises have watched AI agents be confidently wrong. The fix is an agentic context layer, but who has one? (venturebeat.com)
63.
57% of enterprises have watched AI agents be confidently wrong. The context layer is the reason why (venturebeat.com)
64.
Google's TabFM skips per-dataset training and still predicts on tables it's never seen (venturebeat.com)
65.
The Annotated JEPA (news.ycombinator.com)
66.
Launch HN: Context.dev (YC S26) – API to get structured data from any website (news.ycombinator.com)
67.
Files over tools: how we built our agent with a virtual filesystem and bash (news.ycombinator.com)
68.
AI changes the economics of software rewrites (news.ycombinator.com)
69.
The AI architecture that let Liberty Mutual shrug off the Fable 5 outage (venturebeat.com)
70.
The foundational elements of AI architecture that IT leaders need to scale (technologyreview.com)
71.
Pruning RAG context down to what the answer actually needs (news.ycombinator.com)
72.
Show HN: ContextCodeCache in Rust (news.ycombinator.com)
73.
Memorizing session transcripts isn't useful (news.ycombinator.com)
74.
Anatomy of Persistent Memory's 3 Layers: Comparing ContextNest, Mem0 and Zep (news.ycombinator.com)
75.
New Alibaba AI framework skips loading every tool, cutting agent token use 99% (venturebeat.com)
76.
AI agents need context everywhere they run, even where the cloud can't follow (venturebeat.com)
77.
Memory Safe Context Switching (news.ycombinator.com)
78.
Memory Safe Context Switching (longjmp, setjmp) in Fil-C (news.ycombinator.com)
79.
Agent confidence on the technical frontier (technologyreview.com)
80.
OpenAI's free GPT-5.5 model makes ChatGPT better at understanding context (engadget.com)
81.
Shopping online? AI can chat—but it still needs context (feeds.feedburner.com)
82.
AI hit the memory wall — now it needs a new context tier (venturebeat.com)
83.
Fine-tuning forgets. RAG leaks context. Hypernetworks build the model your agent needs on demand. (venturebeat.com)
84.
Zero-Touch OAuth for MCP (news.ycombinator.com)
85.
AWS enters the context layer race with a graph that learns from agents, not manual curation (venturebeat.com)
86.
Pinterest launches an experimental AI shopping app called ‘Ask Pinterest’ (techcrunch.com)
87.
SubQ 1.1 Small (news.ycombinator.com)
88.
Don't trust large context windows (news.ycombinator.com)
89.
Context compression finally works in production: new research cuts LLM input 16x without the accuracy hit (venturebeat.com)
90.
How memory tools can make AI models worse (techcrunch.com)
Today's top topics: openai anthropic ai safety apple ai agents iphone 18 pro microsoft nvidia samsung google
View all today's topics →