Claude Code + Opus 4.7 = Ultimate Coding Agent
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
This AI Agent can actually self-evolve… just watch
David Ondrej
28.0k views
Hermes Agent is insane… 100,000+ github stars
David Ondrej
20.4k views
This 100% minimal AI Agent can do anything… just watch
David Ondrej
28.3k views
This 100% self-improving AI Agent is insane… just watch
David Ondrej
34.5k views
This 100% private AI Agent just destroyed Clawdbot
David Ondrej
23.4k views
Claude Code can now make videos, here’s how
David Ondrej
30.7k views
This 100% private AI Agent can do anything… just watch
David Ondrej
24.7k views
Create Anything with Nano Banana Pro, Here’s How
David Ondrej
26.3k views
If you’re still Vibe Coding, you’re falling behind
David Ondrej
45.4k views
OpenAI just destroyed AI coding… Codex 2.0
David Ondrej
74.9k views
Top Comments (10)
The issue is that it costs too much. It isn’t worth it for Swarm Factory. Opus 4.6 performed just as poorly as Sonnet 4.6 for two weeks, apparently without informing customers. Now the truth has been unveiled. Despite being the more expensive model, there is still no guarantee of consistent quality.
Please do a video on the new Codex computer use.
does the caveman mod solve the cost problem with the new tokenizer? :D
I started watching your channel a while back when you had not even 50k subscribers, and in a literally short time you gain 300k subscribers. amazing
Check out Supabase: https://supabase.plug.dev/AdMxDBd
Major AI companys are playing games, taking turns in a round of rock-paper-scissors, boiling the frog?
Thanks, great information as always!
Great video as usual. Just want to mention that 4.7 is based on a model that was trained on 1T while the new Mythos was trained on 10T mostly generated data * I read somewhere else**
One sentence: "Fuck Anthropic"
opus 4.7 on claude code has been a real step up for me, especially on longer refactors where sonnet used to drift after like 40 turns. curious if you've noticed the same or if you mostly use it for greenfield stuff
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
The issue is that it costs too much. It isn’t worth it for Swarm Factory. Opus 4.6 performed just as poorly as Sonnet 4.6 for two weeks, apparently without informing customers. Now the truth has been unveiled. Despite being the more expensive model, there is still no guarantee of consistent quality.
Please do a video on the new Codex computer use.
does the caveman mod solve the cost problem with the new tokenizer? :D
I started watching your channel a while back when you had not even 50k subscribers, and in a literally short time you gain 300k subscribers. amazing
Check out Supabase: https://supabase.plug.dev/AdMxDBd
Major AI companys are playing games, taking turns in a round of rock-paper-scissors, boiling the frog?
Thanks, great information as always!
Great video as usual. Just want to mention that 4.7 is based on a model that was trained on 1T while the new Mythos was trained on 10T mostly generated data * I read somewhere else**
One sentence: "Fuck Anthropic"
opus 4.7 on claude code has been a real step up for me, especially on longer refactors where sonnet used to drift after like 40 turns. curious if you've noticed the same or if you mostly use it for greenfield stuff