Verbose mode doesn’t impact token usage. Maybe you were just using it for a particularly token-intensive task?
LLMS
-
User reports stable Opus 4.6 performance with 1m context window
By
–
I exclusively use 1m, haven’t noticed issues with opus 4.6
-
Claude’s 1M Context Window: Users May Not Need Extended
By
–
With 1m context window, most users don’t need it anymore. If you miss it, ask claude to re-enable it in your settings.
-
MCP is Back: Claude Codes Can Now Communicate with Each Other
By
–
MCP is so back https://t.co/0XD8dmgkav
— Jiquan Ngiam (@JiquanNgiam) 21 mars 2026MCP 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 — @jiquanngiam, 2026-03-21 14:52 UTC
-

AI Models Trained to Resist Prompt Injection Attacks
By
–
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
… -
Token Consumption as Flawed SWE Productivity Metric
By
–
The old bad SWE productivity metric: lines of code written. The new bad SWE productivity metric: tokens consumed.
-
The ChatGPT Moment for Biology Has Arrived
By
–
This is what excites me most: the ChatGPT moment for biology is here.
— Chubby♨️ (@kimmonismus) 21 mars 2026
OpenAI itself reiterates this regularly by referring to autonomous AI researchers.
I think many still don't understand what this means.
AlphaFold solved a problem that, until a few years ago, seemed too… pic.twitter.com/Zl6tjFV7KKThis is what excites me most: the ChatGPT moment for biology is here. OpenAI itself reiterates this regularly by referring to autonomous AI researchers. I think many still don't understand what this means. AlphaFold solved a problem that, until a few years ago, seemed too
-
ARC-AGI-3 Launch Expected Next Week, Google to Compete
By
–
ARC-AGI-3 launch next week. I assume google will take the lead and will compete with ChatGPT for leading position pretty soon
-

Eight Different Specialized AI Models Overview
By
–
8 Different Specialized #AI Models
by @ingliguori #LLM #GenerativeAI #ArtificialIntelligence #MachineLearning -

Discussion on AI-generated code and diagramming workflows
By
–
C’est marrant parce qu’hier, certaines personnes m’ont dit que c’est illogique de faire un diagramme après la génération du code. (Alors que ce n’était même pas exactement ce que je disais dans mon post, mais bon ) Mais même en admettant que j’aie dit ça, (ce qui n’est pas le