Browse by Topic
49 themes across 36 expeditions
#agent-framework11 entries
“Solid local LLM runner, but the repo is just a marketing page.”
“The de facto RAG framework, but it's a bloated kitchen sink.”
“Overengineered glue for LLMs that became an industry standard despite itself.”
“Solid self-hosted Copilot alternative for teams that want GPU control.”
“Overengineered LLM gateway that solves problems you probably don't have.”
“The de facto standard for open-source LLM fine-tuning, but not for beginners.”
“Fastest LLM finetuning library, but only if you use their hardware or specific GPUs.”
“Solid local AI server, but not the innovation it claims.”
“The de facto standard for high-throughput LLM serving, but not for beginners.”
“A neat toy for code-gen agents, but not production-ready.”
“Solid Swiss Army knife for LLM CLI work, but not revolutionary.”
#fine-tuning11 entries
“Overengineered LLM gateway that solves problems you probably don't have.”
“The de facto standard for open-source LLM fine-tuning, but not for beginners.”
“The de facto standard for transformer models, but bloated and opinionated.”
“Overengineered SDK for a niche local LLM tool.”
“DSPy: The most important LM framework you're not using yet.”
“Fastest LLM finetuning library, but only if you use their hardware or specific GPUs.”
“Solid local AI server, but not the innovation it claims.”
“Official Mistral inference code: minimal, but don't expect a framework.”
“Over-engineered Swiss Army knife that tries to do everything, masters nothing.”
“Over-engineered AI gateway that confuses complexity with capability.”
“Solid Swiss Army knife for LLM CLI work, but not revolutionary.”
#developer-tools9 entries
“Grafana's official blog on observability, AI, and cost optimization.”
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Spotify engineers share practical AI and automation insights.”
“GitHub's official engineering blog on tools, community, and developer policy.”
“Discord's engineering blog: scaling chat, shipping features, and postmortems.”
“Building and running distributed apps on Fly.io's edge cloud.”
“Cloudflare's engineering blog on building a secure, agentic internet.”
“Tailscale's engineering blog: practical networking and security for modern infrastructure.”
#inference-engine9 entries
“Solid local LLM runner, but the repo is just a marketing page.”
“Essential for training large models, but overkill for most teams.”
“The de facto standard for transformer models, but bloated and opinionated.”
“The de facto standard for local LLM inference, but this repo is just its scripts.”
“Maintenance mode project, use vLLM or SGLang instead.”
“Fastest LLM finetuning library, but only if you use their hardware or specific GPUs.”
“Solid local AI server, but not the innovation it claims.”
“The de facto standard for high-throughput LLM serving, but not for beginners.”
“Official Mistral inference code: minimal, but don't expect a framework.”
#architecture8 entries
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Dropbox engineering scales storage and AI with pragmatic deep dives.”
“Lyft's engineering blog: scaling marketplace ML and experimentation.”
“Slack’s engineering blog: scaling reliability, security, and AI agents.”
“Netflix's engineering blog: scaling entertainment with machine learning and media infrastructure.”
“Building and running distributed apps on Fly.io's edge cloud.”
“The architecture that rewrote the decade — every major language model traces its lineage here.”
#database8 entries
“Building and running distributed apps on Fly.io's edge cloud.”
“The de facto RAG framework, but it's a bloated kitchen sink.”
“Overengineered glue for LLMs that became an industry standard despite itself.”
“Solid self-hosted Copilot alternative for teams that want GPU control.”
“Overengineered LLM gateway that solves problems you probably don't have.”
“Over-engineered Swiss Army knife that tries to do everything, masters nothing.”
“Over-engineered AI gateway that confuses complexity with capability.”
“Solid Swiss Army knife for LLM CLI work, but not revolutionary.”
#security8 entries
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Slack’s engineering blog: scaling reliability, security, and AI agents.”
“GitHub's official engineering blog on tools, community, and developer policy.”
“Cloudflare's engineering blog on building a secure, agentic internet.”
“Tailscale's engineering blog: practical networking and security for modern infrastructure.”
“Solid local AI server, but not the innovation it claims.”
#infra7 entries
“Grafana's official blog on observability, AI, and cost optimization.”
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Dropbox engineering scales storage and AI with pragmatic deep dives.”
“Slack’s engineering blog: scaling reliability, security, and AI agents.”
“Discord's engineering blog: scaling chat, shipping features, and postmortems.”
“Cloudflare's engineering blog on building a secure, agentic internet.”
#llm-library7 entries
“The de facto standard for transformer models, but bloated and opinionated.”
“The de facto standard for local LLM inference, but this repo is just its scripts.”
“Maintenance mode project, use vLLM or SGLang instead.”
“DSPy: The most important LM framework you're not using yet.”
“Solid local AI server, but not the innovation it claims.”
“The de facto standard for high-throughput LLM serving, but not for beginners.”
“A neat toy for code-gen agents, but not production-ready.”
#plugin-system7 entries
“Overengineered LLM gateway that solves problems you probably don't have.”
“The de facto standard for transformer models, but bloated and opinionated.”
“Overengineered SDK for a niche local LLM tool.”
“The de facto standard for high-throughput LLM serving, but not for beginners.”
“Over-engineered Swiss Army knife that tries to do everything, masters nothing.”
“Over-engineered AI gateway that confuses complexity with capability.”
“Solid Swiss Army knife for LLM CLI work, but not revolutionary.”
#deep-dive6 entries
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Dropbox engineering scales storage and AI with pragmatic deep dives.”
“Lyft's engineering blog: scaling marketplace ML and experimentation.”
“Netflix's engineering blog: scaling entertainment with machine learning and media infrastructure.”
“Building and running distributed apps on Fly.io's edge cloud.”
#ml-infra5 entries
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Dropbox engineering scales storage and AI with pragmatic deep dives.”
“Lyft's engineering blog: scaling marketplace ML and experimentation.”
“Netflix's engineering blog: scaling entertainment with machine learning and media infrastructure.”
“Cloudflare's engineering blog on building a secure, agentic internet.”
#performance5 entries
“Grafana's official blog on observability, AI, and cost optimization.”
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Dropbox engineering scales storage and AI with pragmatic deep dives.”
“Netflix's engineering blog: scaling entertainment with machine learning and media infrastructure.”
#scaling5 entries
“Meta's engineering blog: scaling infrastructure with AI, security, and performance.”
“Spotify engineers share practical AI and automation insights.”
“Slack’s engineering blog: scaling reliability, security, and AI agents.”
“Discord's engineering blog: scaling chat, shipping features, and postmortems.”
“Netflix's engineering blog: scaling entertainment with machine learning and media infrastructure.”
#distributed-systems4 entries
“Building and running distributed apps on Fly.io's edge cloud.”
“Cloudflare's engineering blog on building a secure, agentic internet.”
“Tailscale's engineering blog: practical networking and security for modern infrastructure.”
“The paper that gave the industry vocabulary for hard trade-offs — and proved that 'always wrong sometimes' beats 'sometimes unavailable'.”
#product-engineering4 entries
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“Lyft's engineering blog: scaling marketplace ML and experimentation.”
“Discord's engineering blog: scaling chat, shipping features, and postmortems.”
“Tailscale's engineering blog: practical networking and security for modern infrastructure.”
#tutorial4 entries
“HashiCorp's blog on infrastructure security, automation, and multi-cloud management.”
“GitHub's official engineering blog on tools, community, and developer policy.”
“Building and running distributed apps on Fly.io's edge cloud.”
“Tailscale's engineering blog: practical networking and security for modern infrastructure.”
#web-framework4 entries
“Overengineered LLM gateway that solves problems you probably don't have.”
“The de facto standard for high-throughput LLM serving, but not for beginners.”
“Over-engineered AI gateway that confuses complexity with capability.”
“A neat toy for code-gen agents, but not production-ready.”
#compiler3 entries
“The de facto standard for open-source LLM fine-tuning, but not for beginners.”
“Maintenance mode project, use vLLM or SGLang instead.”
“Fastest LLM finetuning library, but only if you use their hardware or specific GPUs.”
#culture3 entries
“Spotify engineers share practical AI and automation insights.”
“GitHub's official engineering blog on tools, community, and developer policy.”
“Discord's engineering blog: scaling chat, shipping features, and postmortems.”
#dx3 entries
“Grafana's official blog on observability, AI, and cost optimization.”
“Lyft's engineering blog: scaling marketplace ML and experimentation.”
“GitHub's official engineering blog on tools, community, and developer policy.”
#embeddings3 entries
“The de facto RAG framework, but it's a bloated kitchen sink.”
“Overengineered glue for LLMs that became an industry standard despite itself.”
“Official Mistral inference code: minimal, but don't expect a framework.”
#observability3 entries
“Grafana's official blog on observability, AI, and cost optimization.”
“Datadog's engineering blog: monitoring everything, everywhere, all at once.”
“Slack’s engineering blog: scaling reliability, security, and AI agents.”
#training3 entries
“Essential for training large models, but overkill for most teams.”
“The de facto standard for open-source LLM fine-tuning, but not for beginners.”
“Fastest LLM finetuning library, but only if you use their hardware or specific GPUs.”