Our team is closely monitoring the market over the weekend as prices fluctuate. We continue to actively assess risk parameters and have an open channel of communication with our partners.

I finished my weekend project: FUCK

FUCK is an ERC20, but 100% written in Brainfuck, I deployed it on Arbitrum and I am airdropping the whole supply

It uses a BIOS written in Huff and a compiler written in Solidity. No shortcuts.

brainfucktoken.eth.link

have a great weekend

In terms of 'reverse money,' I grow ever wealthier

guccitroll

This is a good time for Hayden to admit that Ric Burton invented it

magnet:?xt=urn:btih:9238b09245d0d8cd915be09927769d5f7584c1c9&dn=mixtral-8x22b&tr=udp%3A%2F%2Fopen.demonii.com%3A1337%2Fannounce&tr=http%3A%2F%https://t.co/OdtBUsbeV5%3A1337%2Fannounce

GPT-4 Turbo with Vision is now generally available in the API. Vision requests can now also use JSON mode and function calling.
platform.openai.com/docs/models/gp…

Below are some great ways developers are building with vision. Drop yours in a reply 🧵

Introducing AutoCodeRover
Presenting our autonomous software engineer from Singapore ! Takes in a Github issue (bug fixing or feature addition), resolves in few minutes, with minimal LLM cost ~$0.5 ! Please RT

🧑‍💻 github.com/nus-apr/auto-c…

📝 github.com/nus-apr/auto-c…

[ 1 / 4]

boring ahh eclipse

Holy shit

actually insane

Stoked to announce an Agentic Markets workshop Agentic Markets Workshop @ ICML 2024 at #ICML 2024! ICML Conference

📇 Details: sites.google.com/view/amw-2024/…
✏️ Call for papers: due May 17th
📅 Conference: July 26/27th

featuring GOAT speakers like Tuomas Sandholm, Gillian Hadfield, Ian Gemp Constantinos Daskalakis…

I *WAS* WRONG - $10K CLAIMED!

## The Claim

Two days ago, I confidently claimed that 'GPTs will NEVER solve the A::B problem'. I believed that: 1. GPTs can't truly learn new problems, outside of their training set, 2. GPTs can't perform long-term reasoning, no matter how simple…

No one will remember your onchain trades, the millionaires you minted, the NFTs you shilled, your PNL, none of that. By most standards, you’ll die a loser.

And that’s okay.

Underrated outcome of Anthropic Claude having up to 1m token context length with ~perfect recall: Claude can now confidently handle >250 tools!!

When OpenAI fn calling first came out I think it was Simon Willison who called out that we needed 'deep' functions bc of the context…