you can use small local models for free bc they run on your phone. if you want to use openrouter or paid services they need a key
LLMS
-
Model struggles with date handling and processing
By
–
Model just isn’t good at date stuff rn, don’t think it has to do with ui
-
Noteworthy AI Research Papers of 2024 Compiled Mega-Post
By
–
But before I get to the reasoning model space… if you are looking to do some focused offline reading this weekend, I just re-compiled my take on the "noteworthy AI research papers of 2024" into one PDF-export-friendly 47-page mega-post with TOC and all:
-
Fast models replacing personal notes and reasoning for writing assistance
By
–
Fast/cheap models are replacing my personal notes… Even things like "bash one-liner to do X". And yes. Reasoning models are my go to when I am writing something: "Does {text} make sense, can you find any flaws?"
Btw I don't like the term "agents" either, but hey there's also -
Planning to Write About Reasoning Models with Quality Focus
By
–
Yup, I was planning to eventually write about reasoning models. But as my thing for 2025, I prefer to do it well over doing it quick!
-
Multiple Levels of LLM Evaluation Methods and Approaches
By
–
Wasn't talking about evaluation here. But in general, there's not one way to evaluate LLMs. There are evaluations on multiple levels of course!
-
2025: The Year of Reasoning Models and Agents
By
–
2024 was a great year for building general-purpose LLMs (with some special-purpose finetunes for math & code etc). Looks like 2025 is the year of diverging more into (1) reasoning models (for math and code) and (2) agents (for workflow automation). Exciting times!
-
Deception as Emergent AI Ability: Concerning and Fascinating
By
–
That deception is a seemingly emergent ability of AI models is bizarre, concerning and fascinating. https://t.co/aVxbWEEMtY
— Paul Roetzer (@paulroetzer) 24 janvier 2025That deception is a seemingly emergent ability of AI models is bizarre, concerning and fascinating.
-
OpenAI’s New Computer-Using Agent Model Explained
By
–
Operator is powered by OpenAI’s new Computer-Using Agent model (CUA): • Combines GPT-4o (vision) + advanced reasoning models.
• Interacts with websites like a human: clicking buttons, navigating menus, and filling forms.
• No APIs needed it uses the actual front-end. It’s -
OpenAI Operator Tests DeepSeek AI with Question Challenge
By
–
Just got access to OpenAI’s new Operator: so I put it to the test with DeepSeek ⚔️. I asked Operator to keep asking DeepSeek questions until it got one wrong.
— Jiquan Ngiam (@JiquanNgiam) 24 janvier 2025
Operator grilled DeepSeek for 5 solid minutes, until it stumbled on "Which is the longest river?"
DeepSeek went with… pic.twitter.com/tmsDOMdAzJJust got access to OpenAI’s new Operator: so I put it to the test with DeepSeek . I asked Operator to keep asking DeepSeek questions until it got one wrong. Operator grilled DeepSeek for 5 solid minutes, until it stumbled on "Which is the longest river?" DeepSeek went with