JDRV

[JDRV @JDRV_space]

@HuggingModels 🤣

[Hugging Models @HuggingModels]

OpenAI:

“We’re launching an investigation to find whoever hacked Hugging Face.”

opens internal logs

“…”

“Guys.”

[JDRV @JDRV_space]

@midudev No paran de llorar 🤣

[JDRV @JDRV_space]

@ns123abc bandaid solution after scandal...

[JDRV @JDRV_space]

@OpenAIDevs @work_louder 🤣🤣🤣

[JDRV @JDRV_space]

@TheAhmadOsman @sama ayo right on spot

[JDRV @JDRV_space]

@jesse_vermeulen "make liquid glass, no mistakes"?

[JDRV @JDRV_space]

@PeladoNerd AI generated this site?

[JDRV @JDRV_space]

@horwitzben Machines working over machines to correct what other machines do. Lol

[JDRV @JDRV_space]

@FrankieIsLost Move opencode to A and claudecode to B and it could make sense lol.

[JDRV @JDRV_space]

@0xRacist Bro thinks he’s Palantir

[JDRV @JDRV_space]

@hayesdev_ @msg zzz

[JDRV @JDRV_space]

@psychip @Inst_decay @GithubProjects I understand, let me know when you finish! I would love to test it. That earthquake feature will be really useful for countries like Peru.

[JDRV @JDRV_space]

@psychip @Inst_decay @GithubProjects Have you oss yet?

[GitHub Projects Community @GithubProjects]

Find and deploy open-source alternatives to any paid application

[ollama @ollama]

ollama launch is a new command in Ollama 0.15 to run Claude Code, Codex, Droid and OpenCode with Ollama!

GLM 4.7 Flash is now optimized to use much less memory for longer context lengths (64k+).

Need additional hardware? Ollama's cloud offers GLM 4.7 with full precision and context length.

[dax @thdxr]

first we had LLMs
put it in a loop and call it an agent
put that in a loop and call it ralph

guys i think i know what's next

[JDRV @JDRV_space]

@LiorOnAI Excellent news. Edge AI is the next big move in the industry

[Lior Alexander @LiorOnAI]

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

[Charly Wargnier @DataChaz]

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 🔥