get it here → https://
ai.google.dev/edge/eloquent
TOOLS
-
Google’s Eloquent: Bringing AI to Edge Devices with Open Source
By
–
-
Google Launches Free Offline Speech-to-Text App for macOS/iOS Powered by Gemma 4
By
–
SPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW.
— Charly Wargnier (@DataChaz) 3 juin 2026
Google just dropped its own AI voice dictation app for macOS and iOS.
You get all the premium feats of a paid speech-to-text app without any subscription.
100% FREE. Runs offline. Powered by Gemma 4.
Download link in… pic.twitter.com/0Nv6RBNRfuSPEECH-TO-TEXT STARTUPS ARE OFFICIALLY SWEATING RIGHT NOW. Google just dropped its own AI voice dictation app for macOS and iOS. You get all the premium feats of a paid speech-to-text app without any subscription. 100% FREE. Runs offline. Powered by Gemma 4. Download link in
-
Perplexity’s New Agent Architecture: Python, Sandbox, and Efficiency Gains
By
–
Perplexity stopped treating search as one API call. Its agents now write Python that fans out queries, filters results, and joins evidence in a sandbox. On a 200+ CVE task: 100% accuracy, 85.1% fewer tokens. The SDK is private. The pattern isn't, so lets use it with Hermes?
-
Skeptical CLI user becomes tribalistic after dogfooding Codex app
By
–
When I joined OpenAI, the codex app was still in its early days of being put together and being a staunch CLI user I was quite sceptical! All of that changed when I started dogfooding the app, and within days started feeling this tribalistic instinct to try and delegate as much
-
Coding Agents Need Grep, Not Better Vector Databases
By
–
Coding agents don't need a better vector database. They need grep. Direct Corpus Interaction drops embeddings and lets the agent search raw files with grep, find, cat, and sed, refining each query from what the last one returned. On BrowseComp-Plus: +11.0pp accuracy at $424
-
Vibe coding: It’s a real skill, and here are 6 reasons why.
By
–
"Vibe coding isn't a real skill." Anyone who says this is telling on themselves. Hand the same agent to two people. One ships gold, one ships slop. The only variable is the person using it. That's the textbook definition of a skill. 6 arguments to change your mind:
-
DeepSWE: New AI coding benchmark corrects errors with 1.4% error rate
By
–
The benchmark ranking AI coding agents was wrong 32% of the time. DeepSWE is a new open benchmark that fixes this. Tasks span 91 real codebases, average 668 lines changed, and are written from scratch so no model has seen the answer. Its error rate: 1.4%.
-
Struggling to choose among 1,800 AI developer tools
By
–
I have 1,800 AI developer tools. Can't pick one: https://
x.com/scobleizer/lis
ts
… -
New Codex plugins turn it into role specialists instantly
By
–
We’re making Codex more useful for your work by expanding plugins beyond individual tools. These plugins turn Codex into a specialist for a specific role with a single install, no coding required. Codex can access 62 popular apps and 110 skills for work across sales, data
