正在加载视频...

视频加载失败

LlamaCoder just got a lot better with "high quality" mode! It uses two chained LLM calls (1st call to make a plan, 2nd call to code) to create much better apps.

39,440 次观看 • 1 年前 •via X (Twitter)

12 条评论

Hassan 的头像
Hassan1 年前

This is the first of many improvements I'm making! If you want to see the PR including the prompts I used for this new coding agent, take a look here:

Reown 的头像
Reown1 年前

AppKit is the full-stack toolkit to build onchain app UX 🪄 ✅ Social, Email, and Wallet Login ✅ Embedded Wallets ✅ Crypto Swaps ✅ On-ramp Integrate with just 20 lines of code across 10+ languages for all EVM chains and Solana. Onboard millions of users for free today.

AK 的头像
AK1 年前

nice, also try out gemini-2.0-flash-thinking for making apps here in a similar way:

Hassan 的头像
Hassan1 年前

nice, does pretty well!

Tiger Abrodi 的头像
Tiger Abrodi1 年前

Reminds me a bit how perplexity works?

Hassan 的头像
Hassan1 年前

Directionally yes! I suspect Perplexity is doing a lot more than 2 calls in the background. The secret sauce to these LLMs is breaking down the problem and doing a lot of LLM calls, then aggregating them :)

SimpleCove 的头像
SimpleCove1 年前

You guys are killing it! I just discovered your services yesterday and will be reaching out for a call to discuss a few questions I have about inference scaling for multiple customers.

Hassan 的头像
Hassan1 年前

Thank you, great to hear!

Jon Kurtis ⚡ 的头像
Jon Kurtis ⚡1 年前

When deepseek v3?

Hassan 的头像
Hassan1 年前

Soon! Working on it

CoinCollector 的头像
CoinCollector1 年前

Tried it, really helps the quality, good job

Hassan 的头像
Hassan1 年前

Great to hear!

相关视频