Even with agents like Replit and Bolt available, I find myself turning to @cursor_ai for nearly every dev task.
Here are three reasons & a tip for using it to build crypto agents...
For crypto use cases (like memes and agents), the libraries you want to use the most are not well understood by the @cursor_ai models. 🤦♂️
In order to use viem by @wevm_dev you need to add customs docs and reference them with @ tags in your messages. 🙌
2
2
523
BitNet models are really promising
Looking for more models to try now, but not many are out. Expect we see some good ones released and benchmarked soon.
- gh: github.com/microsoft/BitNet
- fine-tuning instructions (published a month ago): huggingface.co/blog/1_58_llm…
How to deploy a 100B model on your CPU devices? 🔥
Excited to introduce bitnet.cpp, our inference framework for BitNet b1.58 🚀🚀
github.com/microsoft/bitnet
2
718
Cline is open-source alternative to Cursor that runs as a VS Code extension. @sdrzn is putting on an amazing show building this tool with constant shipping
Introducing Cline (formerly Claude Dev), an AI assistant that can use your CLI aNd Editor. v2.0 brings exciting updates: responses are now streamed into your editor, a cancel button for better control over tasks, a new XML-based tool calling prompt resulting in ~40% fewer requests per task + better performance from non-Claude models, search and use any model on OpenRouter (search “free” for no-cost options). More details and benchmarks in the release notes: github.com/clinebot/cline/re…
5
424
Replit extremely good for prototyping server work and worth trying
Bootstrapping a python api, db and web ui can just be tasked to Replit at this point
Best feature: automatic checkpoints to back out of any bad code changes
Some things that I wish worked better with @Replit
- Agent often asks for QA before committing code, but sometimes auto commits buggy code 😭
- All environments use the same db service, so if the dev process wipes the db the deployed version is also nuked 🫡
1
177
Caleb retweeted
Alright folks, let's have some So Extra fun! 🌈
👉 Either reply below with, or tag us in a tweet of, a screenshot of your custom message on the So Extra feed, and we'll send some ETH to the addresses of our favourite messages. 👈
Be creative! We like humour, CT references/memes and hot takes!
The tokens will go directly to the address that publishes the message (but on Eth mainnet), so we recommend using the MetaMask option rather than the in-app burner wallet for better security of the tokens.
If you insist on using the burner wallet, and for a quick guide on how to use So Extra, see the links in the first reply.
Caleb retweeted
🌈 Introducing: So Extra 🌈
A new proof-of-concept app developed on Flashbots' SUAVE.
Live on the new SUAVE Toliman testnet, So Extra is a decentralized auction mechanism that allows users to publish custom messages to Ethereum blocks using the extra data field.
Programmable block space is no longer just about transactions.
Inspired to mimic the Bitcoin genesis block message? So Extra has you covered.
Feel the need to digitally and immutably declare your love for that special someone? That's So Extra!
Links to the app and the blog are below.
Caleb retweeted
1. How could you prove that your server is acting in good faith? Even though this isn’t a real concern for NFTs, honesty can be a major concern for web2/web3 inter-operators (really a web2 concern in general).
So Extra ✨
Sealed bid auction on SUAVE to buy extra data
teapaw.org/calebsheridan/status/1…
Replying to @DistributedMarz
9/ So Extra - eth-data.bid/ - Have you ever wanted to put your twitter handle in the extra data of an Ethereum Execution block? Well for the right price now you can! This SUAVE app utilizes Kettle privacy to ensure that bids are sealed.
1
179
What a week with so many new, powerful models being published recently like Llama3.1, @MistralAI, @AnthropicAI
If you're like me and trying to understand what changes to expect out of an upgrade or even swapping out an entire model, there's a whole world of LLMOps to explore.
(And today I was worried that LiteLLM might need an upgrade to use the latest models on @GroqInc, but it just worked by specifying the right model names from the docs.)
1
1
98













