🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

As someone who often wants to compare how different LLMs do at various tasks, I'm surprised I haven't seen more people hyping OpenRouter. Extremely easy to use, lets you pick whatever combination of models you want, charges per token, nice UX. Highly recommend.

The constant reinvention of front end frameworks has finally stopped because frameworks are now selected for their LLM legibility. New frameworks are definitionally outside of the training set and will therefore never catch on.

Ranking of LLMs by the % of JSON violations we detected over the past week, for the top Structured Output requests ⭐️ Qwen, Mistral, and GPT-4o-mini generally doing the best ‼️DeepSeek v3, Sonnet 4 seeing violations north of 20%

Not sure what I've been doing to that caused me to receive a targeted Sotheby's ad for this on Instagram, but I'll try to keep it up! sothebys.com/en/buy/auction…

Why is that all designers are expected to have a portfolio, but not engineers? They both make things.

Karpathy at YC startup school calls this the transfer switch of AI. It's hard to keep up with all the LLMs out there. OpenRouter is the go-to place for 2.5M developers to choose from 400+ models with one API. They're serving 100T tokens/yr! Excited to back this special company!

At face value, there is a ~500x cost between the cheapest and the most expensive. But output tokens 3x more expensive than input, and high end models’ reasoning outputs, there’s another order of magnitude — the actual cost difference is close to 5000x!

I liked ChatGPT’s advanced voice more when it was precise like JARVIS and not “yeah, well so, it is true that uhh…”

Weird that 'stringy' and 'stingy' are pronounced completely differently.

The fact that diffusion LLMs exist & work is a pretty strong argument that LLMs are fundamentally different than human intelligence. I can sort of convince myself I might just be a next token predictor — but no f’ing way I’m a diffusion model!

Good judgement, not code, is the new bottleneck. And it's always been the thing in shortest supply.

Coming soon to OpenRouter 🔥

We’re releasing the Artificial Analysis AI Adoption Survey Report for H1 2025 based on >1,000 responses from developers, product managers and executives adopting AI The Artificial Analysis AI Adoption Survey Report examines key trends in AI usage, analyzing adoption rates,

Developers consider an average of 4.7 LLM families with OpenAI GPT/o, Google Gemini and Anthropic Claude being the most popular, and DeepSeek as the top open-weights choice

My Lumina toothpaste finally arrived (frankly I kind of forgot I ordered it). But now I'm too scared to try it. And I do get cavities.

When interviewing a candidate, the goal is to get to a strong yes or no. If the feedback is "they might be good; hard to tell", the interview failed. I fail ~25% of the time -- it's hard! But it's important to understand the goal, and to train your team for it.

I like and value dedicated QA (and believe manual testing still has its place too) BUT if you do it wrong/too early without building a quality culture first, then you get abdication of responsibility from engineering. "I tested the happy path and it works, so here you go QA!".