Are you using Sonnet or Opus? And when you say dumber what specifically?
LLMS
-
Rate Limits and Token Compaction Bugs in API Systems
By
–
If you're seeing lower rate limits than what we publish, or if you're seeing auto-compact earlier than ~155k tokens, that's a bug. /bug to report.
-
Are We Near AGI Flight? Current LLM Capabilities Assessed
By
–
My short essay on LLMs & AGI: Have we reached the 'AGI of flight'? Not even close. Our planes can carry hundreds of passengers across the globe in just a few hours, yet nothing we build matches a godwit flying non-stop for eleven days without rest or the agility of a bat
-
Claude and GPT-5 for coding: shifting away from Cursor agents
By
–
I primarily use Claude with Claude code and GPT-5 in Codex. I rarely use cursor agents anymore.
-

Samsung’s Tiny AI Model Outperforms DeepSeek and Gemini
By
–
5. Samsung’s Tiny AI beats the giants Samsung unveiled the Tiny Recursion Model (TRM), a 7M-parameter AI that outperformed DeepSeek R1 and Gemini 2.5 Pro on reasoning tasks using a self-improvement loop.
-
LLaMA 2 Sparked Open Source LLM Interest
By
–
It definitely kickstarted things for LLMs but it was LLaMA 2 that showed there was interest in opensource models.
-
Qwen 2.5 influence research adoption compared to other models
By
–
not that it's a bad model, but in terms of influence that is yet to be determined Qwen 2.5 is still used to this day in research and experiments, more than any other model – that's a different level of influence
-
Top 5 Most Influential Open Source LLM Releases
By
–
the top 5 most influential LLM releases that defined opensource AI > LLaMA 2 > Mistral 7B > LLaMA 3 > Qwen 2.5 > DeepSeek R1
-
Model Ranking: Clear Performance Gap Among Top AI Systems
By
–
not saying it wasn't a great model, it'd rank 4th in this list, i just wanted clear jump ahead and those 3 delivered that
-

BLAST: High-Performance AI Web Browser Engine with OpenAI-Compatible Interface
By
–
BLAST: AI Web Browser Engine A high-performance serving engine that adds web browsing to AI applications. BLAST provides an OpenAI-compatible interface with automatic parallelization, intelligent caching, and real-time streaming support. Explore this open-source project