One of our best talks yet. Thanks @a1zhang for the amazing presentation + Q&A on Recursive Language Models! If you're interested in how we can get agents to handle near-infinite contexts, this one is a must. Watch the recording here!
LLMS
-
Using ChatGPT for Calculations via Code
By
–
If you want ChatGPT to calculate for you, use this: "[INSERT WHAT YOU NEED TO CALCULATE] Use code."
-
The Dependence of LLMs on Wikipedia Data
By
–
LLMs would be really dumb without the existence of Wikipedia.
-

Cognition SWE-1.5 Speed Optimizations Reach 1881 Tokens
By
–
Just deployed additional speed optimizations for @cognition SWE-1.5. The fastest measured request was an eye watering 1,881 token/s per Grafana dashboard.
-
Frontier Models vs GPT Codex: Speed to Success Comparison
By
–
Even frontier models fail all the time. The difference is we fail in 15 sec and with one more prompt you get the right answer. Time to success = 30 sec. On GPT Codex it takes 22min just to find out it failed.
-

Using LLM Prompts for Startup Bankruptcy Risk Analysis
By
–

Use this prompt to identify the exact fears of why your startup might go bankrupt. Happy halloween. ——————————————–
BANKRUPTCY PREVENTION SPECIALIST
——————————————– #CONTEXT:
Adopt the role of bankruptcy prevention -

Moonshot launches KIMI CLI with MCP support
By
–


Moonshot released KIMI CLI, a command line coding agent with MCP support!
-

SWE-1.5 Model Architecture: Base Model, RL Training, Inference
By
–
How @cognition /
@windsurf new SWE-1.5 model was built (probably), based on piecing together bits of information that was shared. Base model by: @Zai_org possibly GLM-4.6
RL Training: @nvidia on 'thousands' GB200 NVL72
Inference: @cerebras at 950 tks/sec -
Cartesia Sonic-3 Launches on Poe with 100 Voices
By
–
Congrats to the @Cartesia_ai team and thanks for bringing Sonic-3 to Poe.
— Poe (@poe_platform) 31 octobre 2025
You can use it at https://t.co/OIC6uRjktZ, on our apps, or with the Poe API, with full support for the model’s 100 new voices, 42 languages, and human-like expressiveness. https://t.co/B4xjOdbjkiCongrats to the @cartesia team and thanks for bringing Sonic-3 to Poe. You can use it at https://
poe.com/Cartesia-Sonic
-3.0
…, on our apps, or with the Poe API, with full support for the model’s 100 new voices, 42 languages, and human-like expressiveness. -

Language Models Struggle With High School Math Fundamentals
By
–
Language models perform poorly on high-school math? You don't want to hear this, but the problems started in grade-school. The moment we (collectively) found acceptable that mid-tier models could score only 75%-85% on a GSM test set of 1.32k straightforward problems…