Deepak Kumar

4.2K posts

Deepak Kumar banner
Deepak Kumar

Deepak Kumar

@tech_update0

The introduction of numbers as cordinates is an act of violence

India 加入时间 Mart 2012
1.2K 关注187 粉丝
Deepak Kumar 已转推
Charly Wargnier
Charly Wargnier@DataChaz·
🚨 STOP BURNING YOUR TOKENS! If you use Claude Code, you are probably wasting 80% of your context window. I found 10 ace tools that will completely rescue your API bill. 1. Caveman Claude - Literally makes Claude talk like a caveman - Slashes 75% of output tokens with zero loss in accuracy Repo → github.com/juliusbrussee/… 2. RTK (Rust Token Killer) - A blazing fast proxy that filters terminal output - 60-90% reduction and completely dependency-free Repo → github.com/rtk-ai/rtk 3. Code Review Graph - Claude reads only what matters using a Tree-sitter graph - An unbelievable 49x token reduction on huge monorepos Repo → github.com/tirth8205/code… 4. Context Mode - Sandboxes raw output into SQLite instead of your context - A staggering 98% context reduction on logs & GitHub Repo → github.com/mksglu/context… 5. Claude Token Optimizer - Brilliant setup prompts that optimize any project - 90% token savings, taking docs from 11K to 1.3K Repo → github.com/nadimtuhin/cla… 6. Token Optimizer - Hunts down the invisible ghost tokens eating your context - Fully restores and protects your context quality Repo → github.com/alexgreensh/to… 7. Token Optimizer MCP - Adds aggressive caching and compression to your MCP tools - 95%+ token reduction through pure intelligence Repo → github.com/ooples/token-o… 8. Claude Context - Zilliz’s hybrid vector search MCP - Makes your entire codebase the context for 40% less cost Repo → github.com/zilliztech/cla… 9. Claude Token Efficient - Just drop one CLAUDE.md file into your repo - Enforces strict terseness with zero code changes Repo → github.com/drona23/claude… 10. Token Savior - Navigates your code by symbols, not giant files - 97% reduction on code navigation with persistent memory Repo → github.com/mibayy/token-s… ---- [ The god-tier stack ] Pick 2-3 based on what’s draining you: > Massive repo? Code Review Graph + Token Savior > Heavy terminal output? RTK > MCP data dumps? Context Mode > Need an instant fix? Caveman + Claude Token Efficient Most devs are bleeding tokens. Run `/context` in a fresh session and watch the savings roll in 👀
Charly Wargnier tweet media
kaize@0x_kaize

x.com/i/article/2037…

English
124
638
4.2K
744.5K
Deepak Kumar 已转推
Ronin
Ronin@DeRonin_·
10 GitHub repos to spend 60-90% less tokens in Claude Code: 1. RTK (Rust Token Killer) CLI proxy that filters terminal output before it hits your context - 60-90% reduction on common dev commands - one binary, zero dependencies - works with Claude Code, Cursor, Copilot Repo: github.com/rtk-ai/rtk 2. Context Mode Sandboxes raw tool output into SQLite instead of dumping it into context - 98% context reduction on Playwright, GitHub, logs - only clean summaries enter your conversation - works as Claude Code plugin Repo: github.com/mksglu/context… 3. code-review-graph Local knowledge graph that maps your codebase with Tree-sitter - Claude reads only what matters, not the entire repo - 49x token reduction on large monorepos - 6.8x on average reviews Repo: github.com/tirth8205/code… 4. Token Savior MCP server that navigates code by symbols, not full files - 97% reduction on code navigation - persistent memory across sessions - 69 tools, zero external deps Repo: github.com/Mibayy/token-s… 5. Caveman Claude makes Claude talk like a caveman to cut output tokens - 65-75% output reduction - one-line install - keeps full technical accuracy Repo: github.com/JuliusBrussee/… 6. claude-token-efficient one CLAUDE.md file that keeps responses terse - drop-in, no code changes - reduces output verbosity on heavy workflows - best for output-heavy sessions Repo: github.com/drona23/claude… 7. token-optimizer-mcp MCP server with caching, compression, and smart tool intelligence - 95%+ token reduction through intelligent caching - compresses repeated tool outputs Repo: github.com/ooples/token-o… 8. claude-token-optimizer reusable setup prompts for optimizing any project - 90% token savings in 5 minutes - reduces doc token usage from 11K to 1.3K Repo: github.com/nadimtuhin/cla… 9. token-optimizer finds ghost tokens that silently eat your context - survives compaction without losing quality - fixes context quality decay Repo: github.com/alexgreensh/to… 10. claude-context (by Zilliz) code search MCP that makes your entire codebase the context - ~40% reduction with equivalent retrieval quality - hybrid BM25 + dense vector search Repo: github.com/zilliztech/cla… [ how to stack them ]: you don't need all 10. pick 2-3 based on your workflow: > heavy terminal output? RTK > big codebase? code-review-graph + Token Savior > lots of MCP servers? Context Mode > quick fix? Caveman + claude-token-efficient most people are burning tokens without knowing it run /context in a fresh session and see how much is gone before you even type a word your pocket will thank me later :<)
Ronin tweet media
English
89
303
2.7K
345.3K
Deepak Kumar 已转推
Semih Kışlar
Semih Kışlar@semihdev·
Claude Opus 4.7 sistem promptu sızdırıldı.
Semih Kışlar tweet media
Türkçe
14
71
891
96.6K
Deepak Kumar 已转推
Tim Hopper
Tim Hopper@tdhopper·
One of Python’s superpowers is as a high level interface to fast, low-level code. Here’s how to get started writing a Python library with a Rust extension 👇 pydevtools.com/handbook/tutor…
English
4
21
147
6.6K
Deepak Kumar
Deepak Kumar@tech_update0·
$RAVE is falling knife do not try to catch it.
English
0
0
2
168
Deepak Kumar
Deepak Kumar@tech_update0·
lets understand this why this happens Shorts pay longs every hour (e.g., -1% funding). Existing longs get extra money in their account (like a small reward). This reward makes holding long more attractive. → Many people who were sitting on the side (not trading yet) see: “Wow, if I open a long position now, I will also get paid every hour!” So they open new long positions → They buy the coin in the futures market.
Columbus@columbus0x

$RAVE funding rate: -1% per hour. That is 24% per day and - 8,760% APR 🤯 On a $10,000 short, you pay $2,400 in funding - every 24 hours. Not losses from price. Just the cost of holding the position. Let that sink in. Your account is gone in 4 days without $RAVE moving a single cent. This is not trading. This is just supporting the extraction I described below. Don't.

English
1
0
2
52
Deepak Kumar
Deepak Kumar@tech_update0·
lets understand this. It's called cross-exchange perp arbitrage — catching a small price gap without betting if the coin goes up or down. Here is Simple breakdown given below. At that time: Binance → $RAVE at $8.90 Aster → same contract at $9.20 4% price difference for the exact same thing. That's the inefficiency. Like one shop selling the same phone at ₹74,000 and another at ₹77,000. So Traders did this: Long on Binance at $8.90 Short on Aster at $9.20 Same size both sides. Position becomes neutral — they don't care if $RAVE pumps or dumps. After some time, both prices become equal (say $9.05). They close both:Binance long: +0.15 profit Aster short: +0.15 profit So total profit almost 4% profit.
cryppi / perpdexlist@cryppimagic

$RAVE arbitrage: ~4% price spread, farming 0.53103% funding per hour (~4650% apy) another crime just happened, raveDAO token literally a token for crypto rave community got pumped to ~10b fdv, that’s already top-15 among all tokens lol this pump creates some inefficiencies. long $RAVE on binance at ~8.9 (at the time of writing) short $RAVE on aster at ~9.2 and capture the ~4% spread usually situations like this come with funding against you, but at current rates we should be farming ~0.5% per hour but there’s one catch.. you will most likely get liquidated lol and yeah, you can find setups like this on my site perpdexlist.com

English
0
0
0
374
Columbus
Columbus@columbus0x·
$RAVE funding rate: -1% per hour. That is 24% per day and - 8,760% APR 🤯 On a $10,000 short, you pay $2,400 in funding - every 24 hours. Not losses from price. Just the cost of holding the position. Let that sink in. Your account is gone in 4 days without $RAVE moving a single cent. This is not trading. This is just supporting the extraction I described below. Don't.
Columbus tweet media
Columbus@columbus0x

$RAVE is engineered extraction. It will will dump 95%+ using the same old playbook over and over, and retail will get wrecked like always. Here's how they are doing it. 🧵

English
29
30
335
82K
Wu Blockchain
Wu Blockchain@WuBlockchain·
Just In: Hackers minted 1 billion DOT tokens on the Ethereum mainnet and then sold them off. According to Certik, the attack was primarily due to a Hyperbridge gateway vulnerability, which allowed attackers to forge messages and manipulate the administrator of a Polkadot token contract on Ethereum, profiting approximately $237k.
Wu Blockchain tweet media
English
100
129
737
292.3K
Deepak Kumar 已转推
ayush🔮👨‍💻🔮
ayush🔮👨‍💻🔮@ayushagarwal027·
Stop memorizing Rust rules. Start deriving them. 🦀 This free interactive course reframes the borrow checker not as a set of rules to memorize, but as the logical outcome of three primitives: Space, Time, and Coordinates. 📐 Every memory bug is just a failure in one of these three dimensions: 🔸 Use-after-free 🔸 Dangling pointer 🔸 Data race 🔍 Understand the framework, and the compiler's behavior clicks into place. ✅ 💡 Highly recommended for experienced devs, especially those with a C/C++ background. 👇 jadnohra.com/learn-rust/ #Rust #RustLang #Programming #SystemsProgramming #SoftwareEngineering
ayush🔮👨‍💻🔮 tweet media
English
2
19
167
7.3K
CZ 🔶 BNB
CZ 🔶 BNB@cz_binance·
I typically ignore all these false claims attacks. But... You can apologize now. I am officially divorced. I won't post any legal docs online, as I respect privacy of my ex-wife, and I appreciate the time we spent together. I am happy to bet $1 billion USD (or any number you choose) that: I am officially divorced (way before today). If you agree to take the bet, we can get lawyers to validate my divorce agreement, which should be dead simple. This bet offer is valid permanently, whenever you feel ready. But if you don't take it within 24hrs, it clearly shows who has been mis-representing to the public. Moving on to better things to do.
Star_OKX@star_okx

If he can produce a divorce agreement signed by both parties as of today, I will immediately issue a public apology. If he cannot, yet claims in the media and in his book that he is already divorced, then that is a clear misrepresentation to the public — yet another example of him making such claims with confidence.

English
2.8K
589
7.4K
3.4M
Deepak Kumar 已转推
Abhishek Singh
Abhishek Singh@0xlelouch_·
Recently a friend of mine moved to japan, he got a job in Rakuten, was discussing with him why japan? why not europe (he had an offer there too). Japan SWE salaries aren’t US-level, but the trade can still make sense. 1. Typical range: ¥6M to ¥12M (₹33L to ₹66L). Big tech can go higher. 2. Why move: safer cities, clean public infra, strong passport, predictable life. If you want “calm + competence”, Japan does that well. 3. What to watch: taxes + pension are real. Also, some companies still cap growth if you don’t speak Japanese. How to find roles: 1. Target English-friendly companies first: Rakuten, Mercari, Line, PayPay, SmartNews, and foreign multinationals in Tokyo. 2. Use Japan-specific channels: Japan Dev, TokyoDev, LinkedIn with “visa sponsorship”, and recruiters who actually place in Japan. 3. Interview prep: system design + practical coding. Japanese resumes matter less than clear impact and stable work history. So if you’re optimizing for life, not just comp, Japan is a legit option.
English
20
21
592
80.2K
Deepak Kumar
Deepak Kumar@tech_update0·
Anthropic Mythos unleashed
UnveiledChina@Unveiled_ChinaX

If this is real, it could be one of the largest data breaches in China’s history. A hacker group claims it extracted over 10 petabytes of data from a state-run supercomputing facility, widely believed by experts to be the National Supercomputing Center in Tianjin. This center supports thousands of clients, including research institutes, aerospace programs, and defense-linked organizations. What’s reportedly in the data: - Documents marked “secret” in Chinese - Missile and bomb schematics - Aerospace and aviation research - Bioinformatics and fusion simulation data - Files linked to major state entities like AVIC and COMAC Cybersecurity experts who reviewed sample data say it matches what you would expect from such a facility, though the full breach is not independently verified. Even more concerning: - The attacker claims access lasted months without detection - Sample datasets were posted online via Telegram - Full access is reportedly being sold for hundreds of thousands of dollars in crypto At this stage, the scale and origin are still being verified. But if even partially true, it points to a serious vulnerability in infrastructure tied to China’s scientific and defense ecosystem. If a centralized system like this can be penetrated, what does that say about the security of the data it was processing? #China #Cybersecurity #CCP #DataBreach #Geopolitics #Tech cnn.com/2026/04/08/chi…

English
0
0
0
25
Deepak Kumar
Deepak Kumar@tech_update0·
CIA's "Ghost Murmur" tool can supposedly detect a person's beating heart from up to 40 miles away using advanced sensors and AI — meaning "if your heart is beating, we will find you." 😮
Collin Rugg@CollinRugg

NEW: The CIA used a secret tool called "Ghost Murmur" that uses AI to find heartbeats to rescue the U.S. airman who was stranded in Iran, according to the New York Post. The secret technology was allegedly used for the first time in the field, according to the Post. "The secret technology uses long-range quantum magnetometry to find the electromagnetic fingerprint of a human heartbeat and pairs the data with artificial intelligence software to isolate the signature from background noise," the Post reported. "It’s like hearing a voice in a stadium, except the stadium is a thousand square miles of desert," the source said. "In the right conditions, if your heart is beating, we will find you." "The name is deliberate. ‘Murmur’ is a clinical term for a heart rhythm. ‘Ghost’ refers to finding someone who, for all practical purposes, has disappeared..." "Advances in a field known as quantum magnetometry, specifically sensors built around microscopic defects in synthetic diamonds, have apparently made it possible to detect these signals at dramatically greater distances." CIA Director John Ratcliffe appeared to hint at this technology on Monday, saying the CIA possessed "unique capabilities" but said he couldn't "tell you everything that you want to know." President Trump also revealed during the press conference that the CIA spotted the officer from about "40 miles away." Insane.

English
0
0
0
51
𝙑 🏹
𝙑 🏹@RKs_Tilllast·
Corn Field Chase? What?
English
101
154
2.3K
504.6K
Deepak Kumar
Deepak Kumar@tech_update0·
@malhotra_namit background score is top notch. but the trailer is mid and seems synthetic
English
0
0
35
1.9K
Namit Malhotra
Namit Malhotra@malhotra_namit·
Rama is the greatest of all time because he lived a life where the choices he made were always in the benefit of the greater good, duty over desire, and sacrifice over self. His legacy continues to enhance and empower humanity over time and bring the belief in the goodness of the human spirit to resolve all conflict and bring peace to the world. Namit Malhotra’s Ramayana Directed by Nitesh Tiwari In cinemas worldwide Ramayana Part 1 Diwali 2026
English
2.2K
3.7K
23.9K
3.2M
Sahil Kumar
Sahil Kumar@sahil_kr_·
@malhotra_namit Weak detailing by nitesh tiwari. Whom is this child bowing to? Lord Shri Rama has already moved ahead.😭😭 Not expected this from a 4000cr+ budget movie.
Sahil Kumar tweet media
English
57
62
1.3K
38.1K