How I use LLMs
Karpathy tours the practical differences between the major models as a daily user; great intuition-builder.
Watch on YouTube youtube.com →
Building & Product
Video
Podcast
Article
Article
Article
Article
Article
Article
Article
Guide
Article
Article
Article
Tool
Tool
Tool
Tool
Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in?
There is no best model, only a best model for your task at your price: test the top two or three on your own real examples rather than trusting benchmark headlines. Design your code so the model is a swappable config value (a thin gateway or SDK abstraction does this), because prices and leaders change every few months. Open-source models make sense once you have scale, strict data constraints, or a narrow task; for most first features a hosted API wins on speed to ship.
Go deeper
17 resources.
The 10 Trillion Parameter AI Model With 300 IQ (Lightcone)
YC partners on how model progress should shape what founders build now versus wait on.
Open creators.spotify.com →Claude vs ChatGPT vs Copilot vs Gemini: Enterprise Guide
A structured comparison across reasoning, coding, context, and compliance rather than hype.
Open intuitionlabs.ai →Who Wrote it Better? Claude vs ChatGPT vs Gemini
Side-by-side output quality on real writing tasks, the kind of eval founders should copy.
Open blog.type.ai →LLM Benchmarks: GPT-5, Claude, Gemini, Grok compared
Explains what each benchmark measures so you stop choosing models on a single headline number.
Open futureagi.com →The Best Open-Source LLMs
A serving-infrastructure company's practical map of the open-weight landscape.
Open bentoml.com →Comparing Open-Source vs Closed LLMs for Enterprise Apps
A decision framework for the open-vs-closed call, written for teams shipping to customers.
Open techcommunity.microsoft.com →Open Source vs Closed LLMs: Technical Comparison
Covers the hybrid pattern most teams actually land on: closed for frontier tasks, open for private or high-volume ones.
Open hakia.com →Helicone vs OpenRouter: Key Differences
From an India-founded ML platform: how gateways make model choice reversible.
Open truefoundry.com →LLM Gateway guide: OpenRouter vs LiteLLM vs Portkey vs Helicone
The lock-in insurance layer compared hands-on, including India-built Portkey.
Open klymentiev.com →6 best LLM gateways for developers
A second, eval-minded view on routing layers so you can switch providers in an afternoon.
Open braintrust.dev →Most powerful LLMs (Large Language Models)
A regularly refreshed plain-English rundown of the current frontier models and their sweet spots.
Open codingscape.com →Things we learned about LLMs in 2024
The most-cited year-in-review; explains why the leader changes constantly and why lock-in is a trap.
Open simonwillison.net →LLM Leaderboard: Comparison of over 100 AI models
The independent standard for comparing intelligence, speed, and price on one chart.
Open artificialanalysis.ai →LLM Stats: Compare 300+ models by intelligence, speed, price
Continuously updated rankings pulled straight from provider APIs; good second opinion.
Open llm-stats.com →Vellum LLM Leaderboard
Product-builder-oriented leaderboard that maps benchmark scores to practical use cases.
Open vellum.ai →Price Per Token leaderboards
Fastest way to sanity-check what any model actually costs before you wire it in.
Open pricepertoken.com →More in AI in Your Product
- Should my startup add AI features, and which ones actually matter to users? 20 →
- How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)? 19 →
- How much does it cost to run AI features, and how do I keep costs sane? 19 →
- How do I test whether my AI feature actually works before launch (evals, in plain terms)? 18 →
- How do I stop my AI feature from making things up in front of customers? 17 →
- Prompt engineering, RAG, or fine-tuning: which one does my product actually need? 18 →
- How do I design AI features people trust (chat vs buttons, streaming, showing the work)? 18 →
- What is my moat if I'm building on someone else's model? 19 →
- Should I put an AI agent in my product, or is a simple workflow enough? 18 →
- Is it safe to send customer data to AI APIs, and what about privacy laws like India's DPDP Act? 18 →
- How should I price AI features: per seat, per use, or per outcome? 17 →
- My AI feature is live. How do I monitor it and make it better with real usage? 18 →
Also in Starting Up
The same ground, over in Build the product, our Starting Up track.
eChai Partner Brands
