A top-20 Polymarket leaderboard quant team posted a research paper and deleted it 20 seconds later. I managed to screenshot it. $500โ$2,000 a day. I showed it to a guy in the top-50 leaderboard. He replied: โWhere did you get this? Delete it. Donโt you dare share this document.โ Send both pages to your OpenClaw and ask it to build the bot. Everything you need is inside
โถ@TheAhmadOsmanAfter a couple hours of work, I finally finished developing my first ever skill. :D
Claudeโs frontend skill tells the AI to "pick an extreme aesthetic" and "be creative."
The problem tho is LLMs are just based on probability. Without strict rules, they statistically default to the most likely patterns, that's where AI slop comes from.
To get clean and production-grade UI, you need to override these biases with some engineering constraints.
I open-sourced Taste-Skill to fix this. :)
Check it out! https://github.com/Leonxlnx/taste-skill
(still early lots of improvements are on the way)@LexnLin
โถ@abouelatta_ali
โถ@ctatedev
@every
@om_patel5
โถ@iannuttallOpus 4.5 + Ralph Wiggum with XcodeBuild and playwright is going to mint millionaires.
Mark my words.
Youโre not ready@hunterhammonds
โถ@whosjunaidd
@OpenRouterโก 10+2the fact that http://pi.dev agent is so good, with virtually no sophisticated harness whatsoever, is a testament to the fact token vendor (codex/claude) agents are overrated. highly.
today's moat of codex/claude tools is GIVING TOKENS FOR FREE LEFT AND RIGHT to make you dependant@krzyzanowskim
@dhruvtwt_
โถ@hyperbrowser
@chrstnerodeโก 11+11Top 5 local LLMs:
1. GLM-4.5-air: best agentic/coding model that runs on consumer hardware at very decent speeds. Rivals Claude 4-sonnet.
2. Nousresearch/hermes-70B: the only model that will do whatever you ask, and tell you whatever you want to know. Literally critical to have.
3. GPT-OSS-120B: very intelligent itโs like having 4o at home, great context window, great agent
4. Qwen3-coder-30B-3A-instruct: very good coding agent, excellent workhorse, incredibly fast
5. Mistral-magistral-small: very fast, excellent agent, great coder, multimodal, punches way, way, above its size.
I would be okay never using a proprietary llm, although given the subsidised compute I will continue to use them since Iโm getting free leverage.@0xSeroI built http://markdown.new
Put http://markdown.new/ before any URL โ get clean Markdown back.
Cloudflare's Markdown for Agents is great, but only works for enabled sites. http://markdown.new works for ANY website on the internet.
80% fewer tokens. Also converts PDFs, images, audio.
Free. No signup.
http://markdown.new@elbeyogluAnnouncing Paper Desktop + MCP
Now any agent can read or write with Paper
Paper is connected. To your code. To your agents. To your data. To your teammates.
Download Paper Desktop at http://paper.design@paper
@affaan
โถ@_avichawla
โถ@coreyhainesco
@LiorOnAI
@bbssppllvv
@DhravyaShah
@Dr_SingularityWe're opening the waitlist for our Monetization Gateway, which will allow you to charge for any web page, dataset, API, or MCP tool behind Cloudflare. The charges will settle in stablecoins over the x402 open protocol. https://cfl.re/4eUFdt6@Cloudflare
โถ@vercel_dev
โถ@stephenhaneyโก 3Techniques I'd master if building RAG systems that actually work:
Bookmark this.
1. Sliding Window Chunking
2. Semantic Chunking
3. Document Hierarchies
4. Metadata Enrichment
5. Query Expansion
6. Hybrid Search
7. Reranking Models
8. Context Window Packing
9. Lost in the Middle Problem
10. Hypothetical Document Embeddings (HyDE)
11. Multi-Query Retrieval
12. Contextual Compression
13. Sentence Window Retrieval
14. Auto-Merging Retrieval
15. Cross-Encoder Rescoring
16. Temporal Context Decay
17. Negative Sampling
18. MMR (Maximal Marginal Relevance)
19. Graph-Based Retrieval
20. Recursive Retrieval
21. Citation Trackingchunks
22. Context Ablation Testing
23. Adaptive Retrieval@athleticKoder
@heynavtoor