BasketteCase

Anthropic is burning customer goodwill over something they already know how to fix They price every API call to the cent but won't tell subscription users what their plan actually buys People can accept tighter limits What they can't accept is being told they all started using Claude wrong on the same day People are reporting 40% of their Pro limit gone in 2 prompts. Full weekly allowances drained in 19 minutes. Single-word messages eating 1-4% of sessions That is not a context window problem. It's a transparency problem Anthropic is precise where it benefits them and vague where it protects them The API pricing page is exact: Opus 4.6 runs $5 per million input tokens and $25 per million output. Every call metered The subscription page says "more usage" and "5x or 20x more usage than Pro" More than what? Anthropic has never published how many tokens each plan gets You can see what percentage of your limit you've used, but you can't see what the limit actually is. And you have no way to verify that what you're getting today is the same as last month When Codex users started hitting rate limits faster than expected, OpenAI reset everyone's limits while they investigated. They said they didn't fully understand why and chose the cautious path Anthropic's response was to tell paying users to downgrade - Switch from Opus to Sonnet - Turn off extended thinking - Cap your context at 200k instead of the 1M they advertise - Start new sessions instead of resuming old ones In short, 'this is a skill issue' Every one of those is a feature people are paying to access Paying users should not have to reverse-engineer what their plan buys If Anthropic wants to rebuild trust, the fix is straightforward - Publish actual token budgets per tier, the same way they already do for the API - Show what each message costs against the budget - Let people verify for themselves whether the deal changed They already do this on the API side. The choice not to do it for subscriptions tells you everything

The hottest new programming language is English

@GergelyOrosz or the US govt could've announced Claude was used for some wartime activity and hacker groups immediately went to work. Not saying that happened, but timing seems suspicious.

On one end, the Anthropic team is a massive user of AI to write code (80%+ of all code deployed is written by Claude Code). They ship amazingly fast. On the other hand, seeing these beyond terrible reliability numbers suggests there might be a downside to all this speed:

hot take: any software engineer who is not already at close to 100% ai coding output should be cut within the next 3 months not only are they inefficient, but they’ve also shown a lack of curiosity and willingness to learn

BREAKING: The vast majority of software was slop long before vibe coding was a thing

@claudeai I wa already asking it do do a thorough and deep security analysis... this is great!

Introducing Claude Code Security, now in limited research preview. It scans codebases for vulnerabilities and suggests targeted software patches for human review, allowing teams to find and fix issues that traditional tools often miss. Learn more: anthropic.com/news/claude-co…

API Error: 500 {"type":"error","error":{"type":"api_error","message":"Internal server error"},"request_id": #vibecoding #ai #Clawdbot #claudecode

Today, the MCP community is announcing MCP Apps, the first official MCP extension. @code is the first major AI code editor with full MCP Apps support. With MCP Apps, tool calls can now return interactive UI components that render directly in the conversation. Learn more: code.visualstudio.com/blogs/2026/01/…

😭

@Fattmatt123456 @weatherwilly @grok @grok whats this mean for 30028

@weatherwilly @grok what does this mean for nc weather

This is exact trend i am looking for. Notice how model is now realizing the primary low cant cut into the major cold/HP out ahead. The result is the primary low to west redevelops to coast much sooner/colder overall solution. All the models should trend to this.

@v_computer tag

If you want to vibecode agentic apps... i reccomend replying to this post.

This has been said a thousand times before, but allow me to add my own voice: the era of humans writing code is over. Disturbing for those of us who identify as SWEs, but no less true. That's not to say SWEs don't have work to do, but writing syntax directly is not it.

I’ve been working on my Nexus MCP Gateway project in my spare time. I have been rolling our new features as I encounter use cases in the wild and build to solve them. linkedin.com/posts/dbbasket… #AI #MCP #CodeAssistants #AgenticAI

Nexus MCP Gateway: 2026 First Update linkedin.com/posts/dbbasket… #MCP #AI #SpringBoot

This weeks update on my side-project, Nexus MCP Gateway linkedin.com/posts/dbbasket…

@PythonHub Similar thought. github.com/dbbaskette/Duo…

llm-council LLM Council works together to answer your hardest questions. github.com/karpathy/llm-c…

building an interstate highway open to autos and pedestrians when requirements are a foot traffic sidewalk for kids to walk to school.

Nexus MCP Gateway. linkedin.com/posts/dbbasket… github.com/dbbaskette/Nex…

Took #Gemini3 for a spin this AM on some coding tasks. Seems MUCH better, but honestly the quota limit even for me as a subscriber was so low I couldn't get my work done.