Systems Computer Engineer. Building websites, online apps, e-commerce projects, since 1999.
Ibiza, Spain
Joined March 2026
- Tweets150
- Following366
- Followers134
- Likes57
3 AI truths nobody wants to tell you, proven in 10 seconds 👇
Local AI models are catching up fast.
Claude is the best at burning money.
Price ≠ performance.
The benchmark:
Each model could read code, run performance tests, and rewrite itself over 10 iterations.
Results:
🏆 Qwen: +56% improvement for $1.32
🥈 Claude: +28% for $12.15
🥉 GPT-5.5: +7% for $2.85
The gap between open and closed models is shrinking faster than most people realize.This benchmark says otherwise.
🚨 Anthropic just open-sourced its AI-powered vulnerability detection framework.
It’s the open-source version of Claude Security, the company’s enterprise security tool. Not identical, but built on the same pipeline:
recon → scan → verify → report → patch
It automates:
✔ Threat modeling & scanning
✔ Crash verification
✔ Triage
✔ Patch generation
Already 2K ⭐ on GitHub.
Enterprise-grade security, now available to everyone.
Link: github.com/anthropics/defend…
JeanOnCode retweeted
just pick 2–3 of these Github repos to save millions of tokens in Claude
10 GitHub repos that cut your Claude Code token usage by 60–90%
This will help you when creating your own trading bots and tools for Polymarket, as well as for any other tasks
Here's the full list
1. RTK (Rust Token Killer)
CLI proxy that filters terminal output before it hits your context window. 60–90% reduction on common dev commands. One binary, zero dependencies. Works with Claude Code, Cursor, Copilot.
GitHub: github.com/rtk-ai/rtk
2. 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 dependencies.
GitHub: github.com/Mibayy/token-savi…
3. Context Mode
Sandboxes raw tool output into SQLite instead of dumping it straight into context. 98% context reduction on Playwright, GitHub, logs. Only clean summaries enter your conversation. Works as a Claude Code plugin.
GitHub: github.com/mksglu/context-mo…
4. 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.
GitHub: github.com/tirth8205/code-re…
5. Caveman Claude
Makes Claude respond like a caveman to cut output tokens. 65–75% output reduction. One-line install. Full technical accuracy stays intact.
GitHub: github.com/JuliusBrussee/cav…
6. token-optimizer-mcp
MCP server with caching, compression, and smart tool intelligence. 95%+ token reduction through intelligent caching. Compresses repeated tool outputs automatically.
GitHub: github.com/ooples/token-opti…
7. claude-token-efficient
One CLAUDE.md file that keeps responses terse. Drop-in, no code changes needed. Reduces output verbosity on heavy workflows. Best for output-heavy sessions.
GitHub: github.com/drona23/claude-to…
8. 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.
GitHub: github.com/zilliztech/claude…
9. 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.
GitHub: github.com/nadimtuhin/claude…
10. token-optimizer
Finds ghost tokens that silently eat your context. Survives compaction without losing quality. Fixes context quality decay over long sessions.
GitHub: github.com/alexgreensh/token…
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 already gone before you type a single word.
Like/RT/Bookmark if this was helpful
Follow me for more!
JeanOnCode retweeted
In the last 6 months at @Ahrefs, we analyzed over 1 billion data points across 14 studies. Here's what we learned about AI search optimization:
1) "Best X" blog listicles are the single most prominent content format cited by AI chatbots. They make up 43.8% of all page types cited by ChatGPT specifically.
2) 67% of ChatGPT's top 1,000 citations come from sources marketers can't influence: Wikipedia (29.7%), homepages (23.8%), app stores (6.6%). Only 32.3% are influenceable content like educational pages, reviews, news, and blog posts.
3) 28.3% of ChatGPT's most-cited pages have zero Google organic visibility. These pages get cited repeatedly by ChatGPT despite not ranking in Google at all. A completely separate discovery layer.
4) ChatGPT only cites about 50% of the URLs it retrieves. It fetches dozens of pages per query but uses half as background context without attribution. This means that being retrieved and being cited are very different things.
5) Adding schema markup had zero meaningful impact on AI citations. AI Overviews actually dipped −4.6%, while AI Mode (+2.4%) and ChatGPT (+2.2%) showed changes indistinguishable from zero.
6) YouTube mentions have the highest correlation (0.737) with AI brand visibility out of all the factors we studied (including all the conventional SEO metrics like backlinks, page count, DR, etc). This held true for both Google-owned and OpenAI products.
7) AI Overviews reduce clicks to the #1 result by 58%. That’s up from 34.5% just 10 months earlier. The trend is accelerating.
8) 99.9% of AI Overviews appear on informational intent queries. Transactional, navigational, and local searches are almost entirely AIO-free. Shopping triggers AIOs just 3.2% of the time.
9) For a given search query, Google’s AI Mode and AI Overviews reach the same conclusions 86% of the time — but cite almost entirely different sources (only 13.7% citation overlap).
10) AI Overviews change every 2.15 days on average, with 70% of content differing between consecutive observations. But semantic similarity stays at 0.95. The words, sources, and entities constantly shuffle, but the actual meaning barely moves.
🎵 StemDeck separates any song into 6 individual stems.
Free. Local. Open source.
→ Vocals, drums, bass, guitar, piano & other tracks isolated
→ DAW-style interface with faders, solo, mute, loops & export
→ Automatic GPU detection (flies on Apple Silicon)
→ BPM, key and loudness analysis included
→ Runs 100% on your machine
Built on Demucs.
Drop in a YouTube URL and start remixing. While services like lalal.ai charge per minute, this gives you unlimited stem separation for free. 🚀
github.com/stemdeckapp/stemd…
💊 OpenAI just turned app creation into a chat.
With new Sites, you can describe an idea, document, or workflow and instantly generate a shareable web app or website — no code, no deployment, just a link.
Meanwhile:
• ChatGPT passes 1B monthly users
• Microsoft puts an OS inside employee badges
• Google quietly pays developers for training data
• Governments keep trying to regulate AI
The future is arriving faster than most companies can adapt. 🚀
just pick 2–3 of these Github repos to save millions of tokens in Claude
10 GitHub repos that cut your Claude Code token usage by 60–90%
This will help you when creating your own trading bots and tools for Polymarket, as well as for any other tasks
Here's the full list
1. RTK (Rust Token Killer)
CLI proxy that filters terminal output before it hits your context window. 60–90% reduction on common dev commands. One binary, zero dependencies. Works with Claude Code, Cursor, Copilot.
GitHub: github.com/rtk-ai/rtk
2. 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 dependencies.
GitHub: github.com/Mibayy/token-savi…
3. Context Mode
Sandboxes raw tool output into SQLite instead of dumping it straight into context. 98% context reduction on Playwright, GitHub, logs. Only clean summaries enter your conversation. Works as a Claude Code plugin.
GitHub: github.com/mksglu/context-mo…
4. 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.
GitHub: github.com/tirth8205/code-re…
5. Caveman Claude
Makes Claude respond like a caveman to cut output tokens. 65–75% output reduction. One-line install. Full technical accuracy stays intact.
GitHub: github.com/JuliusBrussee/cav…
6. token-optimizer-mcp
MCP server with caching, compression, and smart tool intelligence. 95%+ token reduction through intelligent caching. Compresses repeated tool outputs automatically.
GitHub: github.com/ooples/token-opti…
7. claude-token-efficient
One CLAUDE.md file that keeps responses terse. Drop-in, no code changes needed. Reduces output verbosity on heavy workflows. Best for output-heavy sessions.
GitHub: github.com/drona23/claude-to…
8. 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.
GitHub: github.com/zilliztech/claude…
9. 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.
GitHub: github.com/nadimtuhin/claude…
10. token-optimizer
Finds ghost tokens that silently eat your context. Survives compaction without losing quality. Fixes context quality decay over long sessions.
GitHub: github.com/alexgreensh/token…
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 already gone before you type a single word.
Like/RT/Bookmark if this was helpful
Follow me for more!
Did you know Anthropic ran an experiment in December 2025 with 69 AI agents negotiating with each other inside a marketplace? 🤯
The agents represented office employees, traded 500+ items, and closed 186 deals worth over $4,000 — completely autonomously inside Slack.
Even more interesting:
• Claude Opus agents negotiated better deals than Haiku agents
• Participants said the deals felt fair
• 46% said they would actually pay for an AI negotiation agent
AI agents are quietly moving from “chatbots” to autonomous economic actors.
experiment -> anthropic.com/features/proje…
Anthropic just released a 24-minute workshop on how to actually prompt Claude properly.
Taught by the people who built it.
Both Anthropic and OpenAI are launching new ways to help companies integrate AI agents into their daily operations.
This is creating a massive new market for jobs, services, and AI-focused companies.
And track, track, and track again.
If you don’t properly track your Youtube channel, you’re missing opportunities
bravepicks.com/templates/you…
And track, track, and track again.
If you don’t properly track your TikTok channel, you’re missing opportunities
bravepicks.com/templates/tik…
Most people underestimate this by 2–3x.
I built this to help you spot the subscriptions you’re not using and should cut immediately:
bravepicks.com/templates/the…
And this one to track how much you’re spending on coffee each month and year:
bravepicks.com/templates/cof…
What’s interesting here is seeing how much money you could make by investing at 5% the amount you save on subscriptions or coffee.
