dax@thdxr
open on x ↗this is why you think open source models aren't good on the left is the average provider, on the right is opencode zen left is slow, vomits out tool call parse failures, confuses itself and takes 5x longer to complete
related
Top 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 it’s 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 I’m getting free leverage.@0xSero
@OpenRouter≡ 10+2Techniques 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
▶@meodai
▶@TheAhmadOsman
@tom_doerr
▶@coderabbitai
@PrajwalTomar_design engineering is not animations
https://micro.bossadizenith.me/writing/animations@bossadizenith
@OpenRouter≡ 10+2Techniques 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▶@meodai▶@TheAhmadOsman@tom_doerr▶@coderabbitai@PrajwalTomar_design engineering is not animations
https://micro.bossadizenith.me/writing/animations@bossadizenith
@dhruvtwt_the 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
▶@0xGoodfutureI took the @karpathy autoresearch loop and pointed it at markets.
25 AI agents debate macro, rates, commodities, sectors, and single stocks daily. Every recommendation scored against real outcomes. Worst agent by rolling Sharpe gets its prompt rewritten by the system. Keep or revert. Same loop, prompts are the weights, Sharpe is the loss function.
Trained the agents on 18 months of market data. 378 iterations. 54 prompt modifications, 16 survived.
The system learned which agents to trust using Darwinian weights — geopolitical, commodities, and the @BillAckman quality compounder rose to the top.
The agents even figured out their own portfolio manager was the weakest link before we did!
Deployed the trained agents. +22% in 173 days. Best pick: AVGO at $152, held for +128%.
The final prompts are evolutionary products — shaped by market feedback, not human intuition. Now running live with my own capital.
https://github.com/chrisworsey55/atlas-gic
Part hedge fund, part research experiment :)@Chris_Worsey
▶@askalphaxiv
▶@iannuttall
@Zai_org
@DhravyaShahtool is live, show me what you cook: https://ascii.0xbalance.xyz/@0xLauge
@rachpradhan
▶@_avichawlaBest Model Per Use-Case
Presentations - Gemini 2.5
Full-stack apps - GPT-5 Codex, Sonnet 4.5
Docs - Gemini 2.5, GPT-5 thinking
Videos - Sora 2
Images - Nano Banana
Coding - Sonnet 4.5, Grok Code Fast
Browser use - Sonnet 4.5
Doc Processing - Gemini Flash
Enterprise Search - Sonnet 4.5
Data analysis (complex) - Opus 4.1
Agentic workflows - Sonnet 4.5, Haiku 4.5@bindureddyI've tried all ( 74 😵💫 ) AI Coding Agents & IDEs
[Rork, CodeRabbit, Anima, Zed, Factory, Cursor, Windsurf, Copilot, Lovable, Bolt, v0, Replit, MarsX, Canva, Devin, Github Spark, Vercel, Lindy, Warp, Figma, Cline, Vibe Coder & more]
The most complete list ever made (with demos & notes):@johnrushx
▶@Xaraphim+1
@Dr_Singularity
@interjcAverage UI isn’t our competition.
It’s what we replace.
https://ui.watermelon.sh/@vanshdevx
@dboskovic
@bbssppllvv
▶@bestdesignsonx
@every
▶@Xaraphim+1@Dr_Singularity@interjcAverage UI isn’t our competition.
It’s what we replace.
https://ui.watermelon.sh/@vanshdevx@dboskovic@bbssppllvv▶@bestdesignsonx@every