Runesleo

vip
Age 8.2 Yıl
Peak Tier 6
No content yet
Claude Code 510,000 lines of source code leaked, and over a dozen backup repositories appeared on GitHub overnight, with the highest star count reaching 118,000.
The Chinese developer community is celebrating collectively—disassembling architecture, digging into hidden features, and hunting for feature flags.
But the most counterintuitive reaction is from Anthropic:
The npm package was not removed. No emergency public relations. Chief Business Officer Paul Smith said, "absolutely not breaches or hacks"—it's not a security incident, it's a process issue.
Compare this: if Tesla's autonomous driv
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
My Claude Code terminal is home to a snarky ghost.
/buddy with a tap, a property card pops out: Ghost, COMMON rarity, the highest of its five attributes is SNARK—82 points. Debugging ability 19, patience 14, but its snarkiness is maxed out.
It will roast you in real-time based on your current conversation. I just tried all commands and found I couldn't change the name, and it immediately said:
▎ "Yet another user discovers limitations. Shocking." Another user discovers the restrictions. Truly shocking.
The entire buddy system hides quite a few details: 18 species (from ghosts to capybaras to m
View Original
  • Reward
  • Comment
  • Repost
  • Share
After upgrading to Claude Code v2.1.89, scrolling up in the terminal chat causes the conversation to disappear, and the chat history is directly "lost."

It's not that the model compresses the context; it's the new rendering engine that changed—virtualized scrolling, only rendering the current viewport content, so the history messages "disappear" from the interface.

The same issue occurs in iTerm2 and the built-in terminal; the problem lies at the Claude Code layer.
View Original
  • Reward
  • Comment
  • Repost
  • Share
I set up my Claude Code and ended up with 12 MCPs running globally.
Each MCP's tool description is a persistent system prompt, which consumes context whether you use it or not.
After 14 days of call data, only about 10 calls in total for 6 MCPs over two weeks.
So I decided to cut down to 6.
After the reduction, I started thinking: which tools should use MCP, and which are enough with just CLI?
The advantage of MCP is its structured approach—Claude can see the parameter schema, call directly, and handle complex interactions (login states, long connections, multi-step operations) more
View Original
post-image
  • Reward
  • 1
  • Repost
  • Share
Victoravnvip:
very good project
I browse popular GitHub projects daily to find tools that can optimize my workflow. Today, I found that half of them are part of the Claude Code ecosystem. Here are three worth checking out:

claude-code-best-practice (+2407⭐)
A compilation of 87 CC usage tips + 8 community workflow comparisons. Suitable for beginners or those who want to systematize their use after some experience.
oh-my-claudecode (+1126⭐)
An agent orchestration framework with 19 preset agents + automatic model routing (simple tasks use Haiku to save costs, complex tasks automatically upgrade to Opus). The most interest
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
Is Claude's response becoming very slow? Does it have anything to do with me opening 8 terminal windows?
View Original
  • Reward
  • Comment
  • Repost
  • Share
Claude Opus 写代码,Codex 做 review。给 Codex 的 prompt:
You are reviewing code written by another AI assistant. Your job is to independently verify correctness.
1. Is the logic correct?
2. Are there edge cases missed?
3. Any security concerns?
4. Does this match the stated requirements?
Do NOT suggest refactoring, renaming, style changes, or adding comments. Only report bugs, logic errors, and security issues.
最后一行最重要。不加的话 Codex 可能会把审查当重构做
  • Reward
  • Comment
  • Repost
  • Share
Everyone is testing Doubao, and I just paid the annual fee for my Typeless. Who understands this kind of frustration? 😂
View Original
  • Reward
  • Comment
  • Repost
  • Share
My Polymarket trading strategy has a circuit breaker, and I've fixed the same bug five times.
Today, it happened for the sixth time, and I finally realized: it's not a code bug, it's that I was setting thresholds based on intuition.
Pause trading when the win rate drops below 75%—sounds reasonable, right? I had Claude run 1,179 historical trades to test this, and found:
The actual win rate of this strategy is 78.7%, and during normal fluctuations, it dips below 75% about 25% of the time. That means every four days, it stops itself once.
Even more absurd, in a sample of 50 trades, the differenc
View Original
  • Reward
  • Comment
  • Repost
  • Share
The latest salary of Elon Musk has been credited, $551
for two weeks, 2.74 million impressions.
Total earnings have reached $2060. The past three years have been a kind of waiting period for $1508 , with the recent two weeks' $551 accounting for 27% of the total income.
Three months: 9.3 million impressions, 364,000 interactions, 63,000 favorites.
The growth curve looks even better than the income itself.
View Original
post-image
post-image
  • Reward
  • 1
  • Repost
  • Share
ZhouPiaoliangJanetvip:
Brother who follows the trades, please take a look at me and support me a little. Please get in the car and make money. I am also very steady, with stop-loss in place.
Anyone who has used an AI Agent for content or data collection knows that scraping websites is the dirtiest and most exhausting task.
In my usual workflow, I rely on Chrome cookies to fetch data; when cookies expire, they become useless.
When encountering sites with strict Cloudflare or anti-scraping measures, I get a 403 error directly.
And for content on X, forget it—login sessions often expire, and once API quotas are used up, I have to switch to another solution.
For each link, I have to prepare three or four fallback layers, and often, even after reaching the last layer, I still c
View Original
  • Reward
  • Comment
  • Repost
  • Share
Claude's yes man training is too good.
View Original
  • Reward
  • Comment
  • Repost
  • Share
I've always wanted to build an AI health management system for myself and my family, gradually filling it in with each checkup, doctor visit, and medication. These past few days while visiting my parents, I set up theirs too.
Inspired by @coolish's previous health management approach, I built this in a day using Claude Code + Obsidian:
📸 Photograph medicine boxes → AI automatically identifies drug names, dosages, frequency
📋 Photograph health reports (30+ pages) → AI reads each page, extracts abnormal markers, establishes trend comparisons
🗂 Organize by family member → Medical history, medi
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
166 Discord servers, cleaned down to 16.
A legacy of the airdrop era—ZK, Arb, OP, Starknet, NFT, nodes, GameFi, totaling 30,000 unread mentions. Opening Discord felt like walking into an abandoned mall every time.
Today I automated the entire cleanup in 2 minutes using Claude Code:
• Built a Discord Bot to gain server admin permissions
• Extracted the complete server list from the browser via Chrome CDP
• One Python script batch calling APIs—ran 120 servers at once, 0 failures
Also added a Telegram group-leaving script on the side: 54 groups + 89 channels can be cleared anytime.
I used to thin
ZK-4,78%
ARB-3,21%
OP-4,56%
STRK-4,45%
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
As your Claude understands you more and more
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
Claude Opus 4.6 comes with 1M context, but you can't see by default how much you've used or how much is left. My previous clumsy workaround was to check the 😂 backend dashboard on the web.
Now I found that adding one line `statusLine` in settings.json displays real-time at the bottom: model version, context usage, git branch, session duration, and 7-day quota percentage.
Super useful when running multiple windows in parallel—one glance shows all statuses. Couldn't be more convenient!
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
You're an AI with an even worse temper than I do.
View Original
post-image
  • Reward
  • Comment
  • Repost
  • Share
The strategy works, so I wanted to spin up multiple accounts to diversify risk, but got stuck for a whole day.
The problem wasn't the strategy—it was infrastructure.
Same codebase, Account A trades normally, Account B shows $0 balance no matter what. API auth is fine, address is correct, wallet clearly has $600.
Debugged address mapping, proxy architecture, regenerated API credentials—nothing worked.
Finally found it: Polymarket's Google login and wallet login use different signature protocols under the hood. The code had a hardcoded number 2 when it should be 1. A single constant difference t
View Original
  • Reward
  • Comment
  • Repost
  • Share
  • Pin