AI News Today | Julian Goldie Podcast

AI News Today | Julian Goldie Podcast

Ornith-1.0 is INSANE (FREE + Local + Open Source)!

10 min · 26. juni 2026
Kom i gang
Billede af episoden Ornith-1.0 is INSANE (FREE + Local + Open Source)!

Beskrivelse

Ornif 1.0 (9B) Local Model Demo: Build Apps Privately, Offline & Free in Agent OSThe video introduces the local AI model Ornif 1.0 (9B) and demonstrates how it’s integrated into an agent operating system to run AI agents locally for free on Mac or PC. The presenter shows Ornif planning and coding a habit tracker in HTML, previewing and saving creations in a workspace, and highlights benchmark comparisons where Ornif outperforms Qwen 3.5 (including some larger models) and Gemma 4 on tests like Terminal Bench. Key benefits emphasized are privacy, offline use, no API costs or limits, and a 9.5GB model building real apps on-device. The script also covers using Ornif with workflows like Hermes, Agent Kanban, local chat, and a loop engine for bug-finding and self-fixing, plus where to get setup help via the AI Profit Boardroom.00:00 [https://www.youtube.com/watch?v=RKu48GBfqO0] Meet Ornif 9B00:38 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=38s] Agent OS Local Setup01:16 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=76s] Building a Habit Tracker02:09 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=129s] Benchmark Breakdown03:30 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=210s] Local First Benefits04:16 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=256s] Previewing the App05:00 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=300s] Using Hermes and Agents06:46 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=406s] Self Fixing Local Engine08:15 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=495s] More Agent OS Workflows09:20 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=560s] Common Objections Answered09:41 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=581s] Join the Community10:37 [https://www.youtube.com/watch?v=RKu48GBfqO0&t=637s] Final Thanks

Kommentarer

0

Vær den første til at kommentere

Tilmeld dig nu og bliv en del af AI News Today | Julian Goldie Podcast-fællesskabet!

Kom i gang

1 måned kun 9 kr.

Derefter 99 kr. / måned · Opsig når som helst

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts
Kom i gang

Alle episoder

639 episoder

Billede af episoden China’s Qwen 3.8 VS Fable 5!

China’s Qwen 3.8 VS Fable 5!

Qwen 3.8 vs GPT-5.6 Soul vs Fable 5 vs Kimi K3: 23 Game Builds Tested (GoldyBench Results)The video compares Qwen 3.8, GPT-5.6 Soul, Fable 5, and Kimi K3 across 23 side-by-side builds on GoldyBench, focusing on game and interactive demo quality such as Outrun, Skyrim-like RPGs, a flight simulator, GTA-style gameplay, Doom-style shooters, physics tests, and landing-page design. The host notes Qwen 3.8 is a massive 2.4T-parameter model and, in these tests, often produces smooth, fun, highly detailed outputs, sometimes with weaker UI, lighting, or buggy controls, while Kimi K3 frequently excels in front-end feel and physics interactions. Fable 5 remains the host’s favorite overall, with Kimi K3 generally second, and GPT-5.6 Soul often competitive but inconsistent. The takeaway is results are a mixed bag, so viewers should test models themselves, with links to GoldyBench and the AI Profit Ballroom community and trainings.

21. juli 202616 min