GENERATIVE AI

Claude Unshipped RAG for Search: Agentic Approach Better

By

–

21 March 2026 16h59

We did RAG early on then unshipped it for a number of reasons: privacy, security, reliability, index staleness. Overall, we found that agentic search gave better results with fewer tradeoffs. If you prefer RAG, we recommend an MCP like Souregraph, or just ask Claude to build a

User reports stable Opus 4.6 performance with 1m context window

By

–

21 March 2026 16h38

I exclusively use 1m, haven’t noticed issues with opus 4.6

Claude verbose mode and contextual information display features

By

–

21 March 2026 16h19

Ask claude to enable verbose mode if you want to see more. If a lot of people want more info for perplexity, we could also show details by default for it or make it configurable. As conversations get longer, we want to give you the info you need while hiding info you don’t need

→ View original post on X — @reach_vb

OpenAI VB Offers Course Support for Students

By

@reach_vb

–

21 March 2026 16h18

hey hey, VB from OpenAI, would be happy to help support you/ your students for the course! DMs open!

Claude’s 1M Context Window: Users May Not Need Extended

By

–

21 March 2026 16h16

With 1m context window, most users don’t need it anymore. If you miss it, ask claude to re-enable it in your settings.

→ View original post on X — @jiquanngiam, 2026-03-21 14:52 UTC

MCP is Back: Claude Codes Can Now Communicate with Each Other

By

@jiquanngiam

–

21 March 2026 15h52

MCP is so back https://t.co/0XD8dmgkav
— Jiquan Ngiam (@JiquanNgiam) 21 mars 2026

MCP is so back Louis Arge (@louisvarge) i made a thing where now any Claude Code can send messages to any other Claude Code on my machine they can ask clarifying questions about work, or become friends — https://nitter.net/louisvarge/status/2035214150545092845#m

→ View original post on X — @simonw

AI Models Trained to Resist Prompt Injection Attacks

By

@simonw

–

21 March 2026 15h49

I think both – plus the labs have been putting a lot of effort into training them to resist prompt injection style attacks Anthropic usually mention prompt injection in their system cards eg this one for Opus 4.6 https://
www-cdn.anthropic.com/0dd865075ad313
2672ee0ab40b05a53f14cf5288.pdf
…