Zum Hauptinhalt springen
YouTube Security VideosRaspberry Pi Book of Making 2027(22.10.2026 um 02:00 Uhr)
•
YouTube Security VideosGoogle Cloud Tech: Which model should I use? | The Agent Factory(22.10.2026 um 01:00 Uhr)
•
YouTube Security VideosTesla: Encore(22.10.2026 um 03:05 Uhr)
••••••
Unix & Linux ServerInternet-Wide Threat Has Security Teams Scrambling to Patch PHP(22.10.2026 um 02:25 Uhr)
•
Unix & Linux ServerDistribution Release: Essora Eos 20261021(22.10.2026 um 02:42 Uhr)
•
YouTube Security VideosRaspberry Pi Book of Making 2027(22.10.2026 um 02:00 Uhr)
•
YouTube Security VideosGoogle Cloud Tech: Which model should I use? | The Agent Factory(22.10.2026 um 01:00 Uhr)
•
YouTube Security VideosTesla: Encore(22.10.2026 um 03:05 Uhr)
••••••
Unix & Linux ServerInternet-Wide Threat Has Security Teams Scrambling to Patch PHP(22.10.2026 um 02:25 Uhr)
•
Unix & Linux ServerDistribution Release: Essora Eos 20261021(22.10.2026 um 02:42 Uhr)
•
Intelligence View
⚡ tsecurity.de Intelligence

Google Cloud Tech: Which model should I use? | The Agent Factory

Video von Google Cloud Tech auf YouTube: Gemini 4 Argon → https://g.dev/ai/gemini-about Google Gemini models → https://g.dev/ai/gemini-models-docs Builders →…

HD Video
Which model should I use? | The Agent Factory
Video abspielen
Beitrag
0
Seite
0
↗ Quelle (Google Cloud Tech)
Social ReaktionenReagiere als Erste:r — dein Feedback zählt!

YouTube Video

Gemini 4 Argon → https://g.dev/ai/gemini-about

Google Gemini models → https://g.dev/ai/gemini-models-docs

Builders → https://g.dev/ai/builder-member-awards



Which Gemini model should developers actually use? While "auto" mode and formal evaluations (evals) are great for production routing, sometimes you just want to build an intuition for when a fast, lightweight model gets the job done, and when you need frontier reasoning to take your project to the next level.



Recorded on-site at Moffett Hangar during Gemini at Work, Luke Schlangen and Mollie Pettit team up with fellow Googlers Jeff Nelson and Gabe Weiss to put Gemini 3.5 Flash-Lite, Gemini 3.8 Flash, and Gemini 4 Argon to the test.



Watch as they run real world mini-evals across four creative developer challenges:

* Live coding music with Strudel.cc.

* Generating Mermaid.js architecture diagrams from video transcripts.

* Automating code-based video editing with HyperFrames.

* Transcribing a folks song into playable mandolin sheet music (and then playing it!).



Chapters:

0:00 - Auto mode, evaluations, and something in between.

2:23 - Planning diagram tests with Mollie

4:07 - Challenge 1: Text-based music generation (Strudel.cc)

5:06 - Music generation results: Flash-Lite vs. Flash vs. Argon

7:05 - Challenge 2: Generating Mermaid diagrams from a video

7:24 - Diagram results: Flash-Lite vs. Flash vs. Argon

12:54 - Challenge 3: Automated video editing & overlays with Jeff

14:41 - Video editing results: Flash-Lite vs. Flash vs. Argon

15:50 - Challenge 4: Transcribing audio to mandolin sheet music with Gabe

17:20 - Sheet music results: Flash-Lite vs. Flash vs. Argon

22:23 - Recap & key takeaways on choosing the right model



More resources:

Learn more about Gemini 3.8 Flash → https://g.dev/ai/gemini-models-38flash-cyber

What exactly is an Agent Harness? (Short) → https://g.dev/ai/youtube-agent-harness



Watch more The Agent Factory → https://www.youtube.com/playlist?list=PLIivdWyY5sqLXR1eSkiM5bE6pFlXC-OSs

🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech



#GoogleCloud #Gemini #GeminiAtWork #Gemini4Argon #GeminiFlash #AIAgents #GenerativeAI



Speakers: Luke Schlangen, Mollie Pettit, Jeff Nelson, Gabe Weiss

Products Mentioned: Gemini, Gemini 4 Argon, Gemini 3.8 Flash, Gemini 3.5 Flash-Lite, Google Antigravity
🔍 CTI & Forensik

Cyber Threat Intelligence & Forensik

ATT&CK-Navigator · IoC-Radar · Exploit-Belege
IoC Intelligence
1 Indikatoren · Defanged · STIX 2.1
strudel[.]cc
CTI Threat Relationship Graph
Akteure · Techniken · Beziehungen
3 Knoten · 2 Relationen
CVE / Incident Threat Actor Software MITRE ATT&CK CWE Weakness IoC
Intelligence Digest — free The top security news daily · unsubscribe anytime
Community Rating & Social Proof
⭐ Leser-Wertung
–
Ø / 5.0
No reader ratings yet
Was this page helpful?
0
Jetzt Bewertung abgeben
🟢 Niedrig (1-3.9) 🟡 Mittel (4.0-6.9) 🔴 Hoch (7.0-8.9) Kritisch (9.0-10.0)

Related story clusters & sources (vector AI)

Pull to refresh
Nächster Beitrag