Tracked topic
…Up until recently, OpenAI’s gpt-oss 20B was my go-to model. With STEM and general knowledge as its strong suit, 20 billion parameters, and up to 128k tokens, I figured…
…The latest update is GPT-5.5 Instant, and it's the default model for all ChatGPT users. It's paired with an upgraded memory system that shows you which past conversations…
…the most tedious parts of working with any AI coding agent: the constant re-explaining. GPT-5.5 is what makes all of this actually work Finally, while you'll always hear…
…Sam Altman described the model as "going from GPT-3 to GPT-5" all at once, which is a fairly bold claim to make. That said, ChatGPT's initial image generation model…
…The only difference this time around would be in the color palette and the theme, which I asked GPT to exercise full control over. Now, since I'd made the cats an…
…For this test, I ran deepseek-r1:14b and gpt-oss:20b on the same laptop equipped with an RTX 5070 and 32GB of RAM. Both models were running locally through Ollama…
…I also find a lot of daily value in custom GPTs. I have built a few personalized bots tailored to my exact writing style and specific formatting rules, which saves me from…
…The second draft for Claude was somehow worse than the first one, meaning ChatGPT's GPT-5.5 model could very easily win some points here over Anthropic's Sonnet 4.6…
…Codex was a step-up A genuine attempt at a game OpenAI's frontier model, GPT 5.4 , has well documented strengths. It is fast, reliable, and unusually consistent with translating plain…
…fine for the things I used it for as a free user, and compared to GPT 5.4, there isn't much to separate them in day-to-day usage. I gave…
