Good catch, that works fine too: uv run –with mlx-audio mlx_audio.stt.generate –help
CODE
-
Claude Code Powers Opinionated Slide Deck Design Tool
By
–
did a whole section on claude design because i'm loving it (like this deck) under the hood, it's claude code with an opinionated ontology on both input (typography, logos, etc.) and output (slides, decks) with further ontology underneath + UI to match if i had to guess, each
-
Q1 AI Launches: Codex, Claude Agents, and Security Tools
By
–
this feels like less a trend and just something we expect… but q1 had a lot of launches that overlapped with recent startups i've seen: – codex desktop for running parallel – managed agents by claude and agents sdk upgrades
– codex security for reviewing code and security
– -
Q1 2025 AI Trends: Coding Models and Autonomous Agents Rise
By
–
feels like forever ago, but had to include openclaw in q1 trends coding models improved greatly in Q4 of 2025, early jan was ppl running claude codes in parallel, and clawdbot blew up late jan models improvement + own computer (mac mini) + channel agnostic communication led to
-
Vibe Coding Adoption Among Professional Developers Survey
By
–
In this informal poll, only a fifth of all coders and software engineers have gone over full time to vibe coding. Most use vibe coding; few use it exclusively. Most still do some hand coding. Amateurs without considerable coding experience should consider carefully.
-
Codex $20 Plan Offers Excellent Value for Developers
By
–
codex with the $20 plan is a really good deal
-
MLX one-liner downloads runs VibeVoice ASR model locally
By
–
Here's a uv one-liner that downloads and runs the MLX model against a local mp3 file uv run –with mlx-audio python -m mlx_audio.stt.generate
–model mlx-community/VibeVoice-ASR-4bit
–audio lenny.mp3 –output-path lenny
–format json –verbose –max-tokens 32768 -
VibeVoice: MIT-Licensed Speech-to-Text with Diarization
By
–
Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good – my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB of RAM at peak and transcribing 1hr of audio in ~9 mins
-
Speed Building vs Methodical Planning: A-B Testing Prototypes
By
–
Very interesting. I wonder, though, does being able to build things very quickly really reduce the need to think and plan methodically? Or are you able to A-B test prototypes quickly, too, to see what works?
-
Wall Hacks Using AR: See-Through-Walls Visual Positioning Technology
By
–
Wall hacks in real life using augmented reality.
— Bilawal Sidhu (@bilawalsidhu) 27 avril 2026
New mad science experiment — I used $300 Meta RayBan glasses and an iPhone to recreate EagleEye's "see-through-walls" tracking.
The answer was visual positioning tech to build a shared spatial map. Code on GitHub.
0:00 – The… pic.twitter.com/qnQ8ApJjgaWall hacks in real life using augmented reality. New mad science experiment — I used $300 Meta RayBan glasses and an iPhone to recreate EagleEye's "see-through-walls" tracking. The answer was visual positioning tech to build a shared spatial map. Code on GitHub. 0:00 – The