Interesante, sobre el rendimiento de ChatGPT Agent en FrontierMath
LLMS
-
LLMs Master NP-Hard Optimization Through Heuristic Reasoning
By
–
By developing heuristic algorithms to tackle challenging NP-hard optimization problems, our LLMs demonstrate their ability to reason, strategically explore solutions, and progressively refine their approach. This highlights our models' capacity for sustained problem-solving,
-
Ailker releases impressive Kontext LoRAs for AI models
By
–
Dang, @ailker is on fire . So many fantastic kontext loras.
-
AI Models Build Web Scraper and UI in Minutes
By
–
Codex implemented the scraper for me in 13 minutes while I was chatting in a coffee shop, then Claude built me the UI (including the calendar export feature) during a subsequent car journey Full details + prompts and transcripts:
-
LLMs Tendency to Generate Excessive SCP Style Text
By
–
Here's an example from over a year ago showing how LLMs just *love* to produce token after token of text in the SCP style!:https://t.co/EUocjpdECI
— Jeremy Howard (@jeremyphoward) 17 juillet 2025Here's an example from over a year ago showing how LLMs just *love* to produce token after token of text in the SCP style!:
-
ChatGPT Agent: Computer Use Like Humans
By
–
When we founded OpenAI (10 years ago!!), one of our goals was to create an agent that could use a computer the same way as a human — with keyboard, mouse, and screen pixels. ChatGPT Agent is a big step towards that vision, and bringing its benefits to the world thoughtfully.
-
ChatGPT’s Self-Reinforcing Distribution Loop and Memory Issues
By
–
This created a self-reinforcing feedback loop. The more in-distribution tokens ChatGPT was getting in its chat history, the more strongly the auto-regressive model was pushed to stay in that distribution. ChatGPT memory made this even worse, letting it happen across chats.
-
LLM Style Mimicry Through Training Data Patterns
By
–
For folks wondering what's happening here technically, an explainer: When there's lots of training data with a particular style, using a similar style in your prompt will trigger the LLM to respond in that style. In this case, there's LOADS of fanfic: https://
scp-wiki.wikidot.com/scp-series -
ChatGPT Gets Computer Access and Computing Capabilities
By
–
ChatGPT gets a computer https://
stratechery.com/2023/chatgpt-l
earns-computing/
…