cristian sanchez

This is who you’re competing against, Chinese fruit seller and chip designer. Yea, you’re cooked:

You can now run 70B LLMs on a 4GB GPU. AirLLM just made massive models usable on low-memory hardware. 𝗪𝗵𝗮𝘁 𝗷𝘂𝘀𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝗲𝗱 AirLLM released memory-optimized inference for large language models. It runs 70B models on 4GB VRAM. It can even run 405B Llama 3.1 on 8GB VRAM. 𝗛𝗼𝘄 𝗶𝘁 𝘄𝗼𝗿𝗸𝘀 AirLLM loads models one layer at a time. Instead of loading everything: → Load a layer → Run computation → Free memory → Load the next layer This keeps GPU memory usage extremely low. 𝗞𝗲𝘆 𝗱𝗲𝘁𝗮𝗶𝗹𝘀 • No quantization required by default • Optional 4-bit or 8-bit weight compression • Same API as Hugging Face Transformers • Supports CPU and GPU inference • Works on Linux and macOS Apple Silicon 𝗪𝗵𝗮𝘁 𝘆𝗼𝘂 𝗰𝗮𝗻 𝗱𝗼 • Run Llama, Qwen, Mistral, Mixtral locally • Test large models without cloud GPUs • Prototype agents on cheap hardware

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on @huggingface 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This @nvidia model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

how my codebase written entirely with claude code runs

btw, this would be a better comparison

Just spotted this in London, are you guys hiring in Europe? @vercel @rauchg

@nikitabier create.

In 2 words, what is your purpose in life?

the last months i've been working on 'self', a virtual machine with native AI integration at both the instruction-set level and the stdlib level. it has its own language, and the demo below takes under 30 lines to write. more details at selfvm.run/research

BREAKING: 🇨🇭🇺🇲 Switzerland REJECTS Palantir Software Palantir Software Poses Devastating Risks - Netz Politik After a risk assessment of the use of Palantir software in Switzerland, the US corporation was rejected, despite years of courting by authorities and the army. The Swiss consider the risks too great. The fear is that Palantir is handing over sensitive data to the US and from there to Israel.

@jarredsumner Hey jarred, are there open roles at bun? I’m 20, working at different startups for the past 4 years. Built “self” a virtual machine built in rust with native AI integration as part of the instruction set. Speaker at community events Everything at asterisk.gallery

first day!

@ahmadaccino yep yep… asterisk.gallery

we're looking for a cracked full stack eng to come in for 4 week sprint to work on an internal product - 4 weeks fulltime in our dope chicago office - potential transition to permanent role - travel and stay expenses covered if you're cracked at sql and node reply or dm

@iyoushetwt there is no plan b

If coding disappears tomorrow, what’s your plan B?

@rauchg @vercel i really think mcp it’s not that bold, it’s only a client server contract. It even does not enforce you a transport layer. It only exposes what you can do, or what you can consume. In fact, without LLM’s it’s something like a functions discovery service

MCP has won. It’s making its way into ChatGPT. This is amazing news for developers and the broader AI ecosystem. You can now use @vercel MCP with it. If you want to ship your own MCPs, check out xmcp.dev.

@carla0st @_buildspace @_nightsweekends awesome idea 🔥 when i am on the street with the headset i open chatgpt 4o and start talking to him with the phone in my pocket. the point of this is, how to handle the end of the statements and how to interrupt the process if you said something wrong, without using the screen on

*dusts off twitter account* i'm launching a summer of projects and here's the first thing i want to make cc @_buildspace @_nightsweekends

@anishthite @_nightsweekends @_buildspace hahahah this idea will be fun. any thoughts around banned topics?

Im tired of making decisions gonna put an angel and devil on my shoulder btw its live if you wanna try it cc: @_nightsweekends @_buildspace

@rds_agi @sonicrypt @solana @burnt_xion @_buildspace @_nightsweekends @FarzaTV I am looking at the project, did you code the esp32 with plain c++? maybe this is useful for you toitlang.org . esp32 hot reload on code changes, it's feels magic.

i think @sonicrypt deserves to be more than just another hobby project for those who are wondering what @sonicrypt is, its basically a physical notification device for blockchain transactions (currently only @solana & @burnt_xion ) cc: @_buildspace @_nightsweekends @FarzaTV

@rds_agi 🔥🔥

20 lines of css, and I got this view-transitions-api 🥰

Elon Musk fired 80% of Twitter (6500 people) and everyone thought that Twitter was doomed. He was right. Everyone was wrong. It’s the management masterclass of the decade and every entrepreneur must understand why it worked 🧵: