Yared's log
https://youtu.be/Y9Wz2PV404E?si=PquRzo216IhJsqsa
Claude mythos is now available for public use with security measures and brand new name its now called Fable
AI Post — Artificial Intelligence
When the model is used for frontier LLM development, it apparently does not simply refuse or warn the user. Instead, it quietly limits its own effectiveness through techniques like prompt modification, steering vectors, and PEFT.
That means Claude may still answer, but become deliberately less useful for building frontier AI systems, pretraining pipelines, distributed training infrastructure, or ML accelerators.
Anthropic says this should affect only around 0.03% of traffic, but the precedent is big: They are being selectively capability-throttled in strategically sensitive domains.
That means Claude may still answer, but become deliberately less useful for building frontier AI systems, pretraining pipelines, distributed training infrastructure, or ML accelerators.
Anthropic says this should affect only around 0.03% of traffic, but the precedent is big: They are being selectively capability-throttled in strategically sensitive domains.
This is why you need to have Local model with your own tools around it
A practical tip for anyone using Codex or AI coding agents on a large codebase:
You must design the codebase in a way that guides the agent.
In CRUder, I made Codex much more effective by setting hard architecture rules and restructuring the project for AI-assisted development:
✦ Split huge files into smaller focused files
• Kept files around 450 to 500 lines max
✦ Added folder-level
• Defined what each folder does
• Explained what each file cover
- This Reduced unnecessary context loading
✦ Built the system in a modular, function-based structure
• Made the codebase easier to inspect
• Made edits safer and more predictable
• Reduced regressions during feature implementation
After this: Codex became more reliable, used context more efficiently.
Good architecture is not only for human developers. It is also how we enable AI collaborators to work at production scale.
You must design the codebase in a way that guides the agent.
In CRUder, I made Codex much more effective by setting hard architecture rules and restructuring the project for AI-assisted development:
✦ Split huge files into smaller focused files
• Kept files around 450 to 500 lines max
✦ Added folder-level
AGENT.md guide files• Defined what each folder does
• Explained what each file cover
- This Reduced unnecessary context loading
✦ Built the system in a modular, function-based structure
• Made the codebase easier to inspect
• Made edits safer and more predictable
• Reduced regressions during feature implementation
After this: Codex became more reliable, used context more efficiently.
AI coding agents are powerful, but they need proper engineering guidance.
Good architecture is not only for human developers. It is also how we enable AI collaborators to work at production scale.
❤2
Yared's log
A practical tip for anyone using Codex or AI coding agents on a large codebase: You must design the codebase in a way that guides the agent. In CRUder, I made Codex much more effective by setting hard architecture rules and restructuring the project for…
This is a significant solution to reduce regressions caused by unrelated fixes.
While building CRUDER initially, the model just kept stacking solutions onto the initial basic files it created, so I lost some progress due to regressions and a disproportionate consumption of context resulting from oversized documents.
So I restructured the project's overall architecture the way I described above, and after that, I have seen no regressions at all, and the token consumption shrank by a good amount.
While building CRUDER initially, the model just kept stacking solutions onto the initial basic files it created, so I lost some progress due to regressions and a disproportionate consumption of context resulting from oversized documents.
So I restructured the project's overall architecture the way I described above, and after that, I have seen no regressions at all, and the token consumption shrank by a good amount.
Yared's log pinned «A practical tip for anyone using Codex or AI coding agents on a large codebase: You must design the codebase in a way that guides the agent. In CRUder, I made Codex much more effective by setting hard architecture rules and restructuring the project for…»
Forwarded from Pearl 𓂀𓍢ִ໋ ͙֒ (Ramen 𓆣)
☆
☆
☆
☆300 m people can't see colors,
☆
☆
So what i am trying to say is...
50 m people are fighting cancer,☆
173k peoole didn't wake up today,☆
80 m people can't walk,☆300 m people can't see colors,
☆
55 m people can't remember memories,☆
430 m can't hear.So what i am trying to say is...
Even if you got problems to deal with ( i am not downgrading them!), your ordinary is someone's dream. So try to be grateful for what you have rn ☺️😗
https://www.youtube.com/watch?v=WNZehEJJPAg&list=RDWNZehEJJPAg&start_radio=1
ተጋበዙልኝ ከልቤ ነው የምወደው በያንዳድዱ ግጥሞቹ ላይ ያሉትን መልእክቶች አዳምጡት ወርቅ እንኳን ከዚ ያንሳል
ተጋበዙልኝ ከልቤ ነው የምወደው በያንዳድዱ ግጥሞቹ ላይ ያሉትን መልእክቶች አዳምጡት ወርቅ እንኳን ከዚ ያንሳል
YouTube
ሮፍናን - ሦሥት III ROPHNAN - SOST
00:00 - ሠው ነህ ይላል III SEW NEH YILAL
05:55 - ሠው ወይስ ሀገር? III SEW WEYS HAGER?
10:05 - ሠከላ III SEKELA
Written And Performed By ROPHNAN
05:55 - ሠው ወይስ ሀገር? III SEW WEYS HAGER?
10:05 - ሠከላ III SEKELA
Written And Performed By ROPHNAN
❤1🔥1💯1
Yared's log pinned «https://www.youtube.com/watch?v=WNZehEJJPAg&list=RDWNZehEJJPAg&start_radio=1 ተጋበዙልኝ ከልቤ ነው የምወደው በያንዳድዱ ግጥሞቹ ላይ ያሉትን መልእክቶች አዳምጡት ወርቅ እንኳን ከዚ ያንሳል»
https://huggingface.co/moonshotai/Kimi-K2.7-Code
Kimi-K2.7-Code is out its specialized for codding and compete with the cutting-edge models
Kimi-K2.7-Code is out its specialized for codding and compete with the cutting-edge models
It's been a while since GPT 5.5 and Cloude Opus 4.7 and 4.8 were out,
but for the first time in the past two months, out of the 11, I stepped back and prefer GPT 5.4 and Sonet 4.6 for many of my tasks.
I felt comfortable there; they do well, cost better, and they have this odd symphony when you use them together. It's empowering, honestly.
but for the first time in the past two months, out of the 11, I stepped back and prefer GPT 5.4 and Sonet 4.6 for many of my tasks.
I felt comfortable there; they do well, cost better, and they have this odd symphony when you use them together. It's empowering, honestly.