barayuda's profile picture.  👋 http://github.com/barayuda Learn & Share #ResearchGate

Barayuda

@barayuda

 👋 http://github.com/barayuda Learn & Share #ResearchGate

Może Ci się spodobać
Barayuda podał dalej

Creates bootable Windows USBs on macOS github.com/TechUnRestrict…

tom_doerr's tweet image. Creates bootable Windows USBs on macOS

github.com/TechUnRestrict…

Barayuda podał dalej

iOS Swift development IDE for Windows and Linux github.com/nab138/CrossCo…

tom_doerr's tweet image. iOS Swift development IDE for Windows and Linux

github.com/nab138/CrossCo…

Barayuda podał dalej

Meta just solved RAG's biggest bottleneck. 30× faster decoding. Zero accuracy loss. The problem nobody talks about: When you feed an LLM 80 retrieved passages, only 5-10 are actually useful. The rest? Dead weight. But you're computing attention for ALL of them. The math is…

techNmak's tweet image. Meta just solved RAG's biggest bottleneck.

30× faster decoding. Zero accuracy loss.

The problem nobody talks about:

When you feed an LLM 80 retrieved passages, only 5-10 are actually useful.

The rest? Dead weight. But you're computing attention for ALL of them.

The math is…

Barayuda podał dalej

Database Scaling Techniques 📘📚 Save it now ✅️ #Database

Krishnasagrawal's tweet image. Database Scaling Techniques 📘📚

Save it now ✅️ 

#Database

Most people are building side projects. But what if your side project was already a real business? We spend months hacking “prototype apps”… but nothing we build ever reaches the App Store. No monetization. No users. No momentum. I thought that’s just how it works—until I…



Barayuda podał dalej

Open-source AI agent platform for financial analysis github.com/AI4Finance-Fou…

tom_doerr's tweet image. Open-source AI agent platform for financial analysis

github.com/AI4Finance-Fou…

Barayuda podał dalej

Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better. I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was…

AndrewYNg's tweet image. Releasing a new "Agentic Reviewer" for research papers. I started coding this as a weekend project, and @jyx_su made it much better.

I was inspired by a student who had a paper rejected 6 times over 3 years. Their feedback loop -- waiting ~6 months for feedback each time -- was…

Barayuda podał dalej

Self-hosted alternative to Vercel and Heroku github.com/raghavyuva/nix…

tom_doerr's tweet image. Self-hosted alternative to Vercel and Heroku

github.com/raghavyuva/nix…

Barayuda podał dalej

Sharing moments shouldn’t depend on the phone you have. Starting today with the Pixel 10 family, Quick Share now works with AirDrop, making secure file transfers between Android phones and iPhones more seamless. This builds on our commitment to cross-OS compatibility to bridge…


Barayuda podał dalej

Today we’re excited to unveil a new generation of Segment Anything Models: 1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts. 🔗 Learn more about SAM 3: go.meta.me/591040 2️⃣ SAM 3D…


Barayuda podał dalej

Today, our team launched Google Antigravity. - Agent-first IDE powered by Gemini 3 Pro 🧠 - Browser control to test your apps automatically 🤖 - Agent Manager to orchestrate parallel agents ♾️ Stoked to keep shipping with the @antigravity team. This is going to be fun.


Barayuda podał dalej

LibrePods unlocks Apple's exclusive AirPods features on non-Apple devices. Get access to noise control modes, adaptive transparency, ear detection, hearing aid, customized transparency mode, battery status, and more github.com/kavishdevar/li…


Barayuda podał dalej

Fastest inference engine for LLMs! LMCache is an LLM serving engine that reduce Time to First Token (TTFT) and increase throughput, especially under long-context scenarios. Here is why it's a game changer: LMCache caches and reuses key-value (KV) pairs from repeated text…

Sumanth_077's tweet image. Fastest inference engine for LLMs!

LMCache is an LLM serving engine that reduce Time to First Token (TTFT) and increase throughput, especially under long-context scenarios.

Here is why it's a game changer:

LMCache caches and reuses key-value (KV) pairs from repeated text…

Barayuda podał dalej

Memory engine for AI Agents with a single line of code. Just call memori.enable() to give any LLM or agent persistent memory. Uses existing SQL database - no vector databases required. 100% open-source.

unwind_ai_'s tweet image. Memory engine for AI Agents with a single line of code.

Just call memori.enable() to give any LLM or agent persistent memory. Uses existing SQL database - no vector databases required.

100% open-source.

Barayuda podał dalej

Massive update for AI Engineers! Training diffusion models just got a lot easier. dLLM is an open-source library that does for diffusion models what Hugging Face did for transformers. Here's why this matters: Traditional autoregressive models generate text left-to-right, one…


Barayuda podał dalej

TOON (Token-Oriented Object Notation) is out for some days now and it aims to make communication with LLMs more accurate and token-efficient. The TOON topic is now one of the hottest news on the LLM market and it might actually matter. 𝗪𝗵𝘆 𝗜 𝘁𝗵𝗶𝗻𝗸 𝘀𝗼: I was…

Aurimas_Gr's tweet image. TOON (Token-Oriented Object Notation) is out for some days now and it aims to make communication with LLMs more accurate and token-efficient.

The TOON topic is now one of the hottest news on the LLM market and it might actually matter.

𝗪𝗵𝘆 𝗜 𝘁𝗵𝗶𝗻𝗸 𝘀𝗼:

I was…

Barayuda podał dalej

we are working on a Rust-based ETL server that can stream your Postgres database to S3/Iceberg (and other databases like BigQuery & ClickHouse) 100% open source, and designed so that it can be embedded in any Rust server

supabase's tweet image. we are working on a Rust-based ETL server that can stream your Postgres database to S3/Iceberg (and other databases like BigQuery & ClickHouse)

100% open source, and designed so that it can be embedded in any Rust server

Barayuda podał dalej

Web interface for Nginx site and SSL management

tom_doerr's tweet image. Web interface for Nginx site and SSL management

Barayuda podał dalej

Let's split the Nuxt directory structure into it's own section in the docs.


Barayuda podał dalej

New book from @PacktDataML >> "Building AI Agents with LLMs, RAG, and Knowledge Graphs — A practical guide to autonomous and modern AI agents" See it at amzn.to/4622k2h

KirkDBorne's tweet image. New book from @PacktDataML >>

"Building AI Agents with LLMs, RAG, and Knowledge Graphs — A practical guide to autonomous and modern AI agents"

See it at amzn.to/4622k2h

Barayuda podał dalej

Your own AI coding platform in one click 🤯 @Cloudflare just open-sourced VibeSDK, letting anyone spin up their own vibe coding environment! → LLM code gen + fixes → Safe runs in CF Sandboxes → Infinite scale via `Workers for Platforms` → GitHub Export Demo + links in 🧵↓

DataChaz's tweet image. Your own AI coding platform in one click 🤯

@Cloudflare just open-sourced VibeSDK, letting anyone spin up their own vibe coding environment!

→ LLM code gen + fixes
→ Safe runs in CF Sandboxes
→ Infinite scale via `Workers for Platforms`
→ GitHub Export

Demo + links in 🧵↓

United States Trendy

Loading...

Something went wrong.


Something went wrong.