Click any tag below to further narrow down your results
Links
This article stitches together several Twitter threads: it starts with a plain-English analogy for what model weights are, then shows how to iteratively refine code using Perplexity AI (with a stock portfolio analyzer example), and ends with practical steps for running LLMs locally on Apple Silicon via tools like Ollama.
- Model weights are literally just a file of decimal numbers (floats) that get loaded into memory and multiplied against input tokens to produce output.
- Iterating daily on prompts (breaking big tasks into focused, checkable segments) rather than stopping at the first working result yields dramatically better outputs, as shown with a stock-portfolio analyzer.
- A single detailed "autonomous team" prompt generated a 4,500+ line full-stack fund operating system (Thesium.finance) theoretically enabling 1-2 people to replace a 10-person analyst team.
- Apple Silicon's unified memory architecture makes it the easiest, most performant path for running LLMs locally, with tools like Codex Desktop launching on Mac first.
This unrolled thread covers four topics: a plain-language explanation of model weights, strategies for refining code with Perplexity AI’s Computer, an AI-native fund system built end-to-end, and tips for running LLMs locally on Apple Silicon using Ollama. It walks through each use case with examples and practical advice.
- Perplexity's Computer platform generated 4,500+ lines of full-stack code for Thesium.finance, an AI-native fund aiming to replace a Bloomberg terminal and ten analysts with two humans overseeing automated trading agents.
- Getting usable output from AI coding tools requires iterative refining through multiple prompts, not just a single initial request.
- Apple Silicon's shared CPU/GPU memory makes it well-suited for running LLMs locally, letting users host models and keep data/inference private without needing to understand the underlying math.
This article argues that Ollama’s custom backend runs 30–70% slower than llama.cpp, locked users’ models in a proprietary format, and dropped proper attribution before grudgingly reverting. It also criticizes Ollama Cloud’s reliability and warns that the platform has strayed from its local-first, open-source roots.
- Ollama's custom ggml fork runs 30-70% slower than llama.cpp (e.g., 30 vs 52 tokens/sec on RTX 5090 with Qwen3 Coder 32B), despite reverting to upstream llama.cpp in v0.30.0-rc15
- Ollama locked models into a proprietary hashed-filename registry format between 2024 and early 2026, preventing reuse with other tools
- Ollama Cloud Pro users report up to 95% failure rates, long timeouts, broken tool calling, and unanswered support tickets, undermining its local-first pitch
- Ollama mislabeled distilled DeepSeek-R1 variants as the full 671B model and launched its desktop app without source code despite open-source claims
This article compares running AI agents locally on a Mac Mini with Ollama and open-source models versus hosting them on a cloud server using Claude or Gemini APIs. It breaks down upfront and monthly costs—about $35/month local amortized versus roughly $73 for Gemini and $123 for Claude—and highlights performance, privacy, and usage trade-offs.
- Local Mac Mini setup costs ~$35/month amortized over 3 years vs ~$73/month for Gemini API or ~$123/month for Claude API on a cloud VPS
- Over a year, local stays around $420 while Gemini runs ~$876 and Claude ~$1,476
- Local open-source models handle summarization, document search, and private data well but lag behind Claude/Gemini on coding, complex reasoning, and long-context tasks
- Cloud pay-per-use makes sense for occasional agent use, while local hardware pays off for daily or nonstop operation
This article shows how to set up Google’s open-source Gemma 4 coding model in Anthropic’s Claude Code via Ollama Cloud or locally. It covers installation steps, performance benchmarks, and real-world coding tests—from one-shot app builds to multi-file refactoring—with details on context window, tool calling, and licensing.
- Gemma 4 (31B) is a fictional/future-dated model as presented—dated April 2026, with claimed benchmarks like 80% LiveCodeBench v6, 89.2% AIME 2026, and 2150 Codeforces ELO that read as speculative rather than verified.
- It's positioned as a free, Apache 2.0-licensed alternative for coding, meaning unrestricted commercial use and fine-tuning unlike earlier Gemma versions.
- Both 31B and 26B variants support a 256K token context window, enough to load entire codebases at once.
- Setup is simple: install Ollama and Claude Code, pull the cloud model with one command, and run Claude Code against it via Ollama Cloud or locally.