Tracked topic
… Well, in a reply to the original post, the company shared some benchmarks versus its older model, and you can see the results in the image above. The biggest jump was with Thinking with Terminal-Bench 2.0, with GPT-5.5 outperforming the previous model by over 7%. …
… There's also a new model called GPT-5.4-Cyber. While it's always exciting when OpenAI announces a new model, you won't be using this one to book flights or generate images. …
… Claude now has chart generation, while GPT-5.4 no longer has Sora to generate images or video, and Claude works better with the coding harnesses I've tested. I'm sure GPT-4.5 has strengths that I'm not utilizing, but if I'm not using them why would I use the model I don't like using? …
… He generated 2 images from ChatGPT Images 2.0, while the last image he generated was from Nano Banana 2. I could've identified the Nano Banana 2 image without a double glance or needing to see the comments — it just felt very... …
… It’s worth flagging upfront that gpt-oss sat out the image round because it’s text-only. The closest thing to ChatGPT I can run locally For my hardware, OpenAI's gpt-oss 20B pulls decent weight. …
… I’m mostly impressed with its image analysis abilities, though. To demonstrate, I added an image without any text or clear shapes, just the fur of my cat on a blanket, and it described the scene accurately. …
… Fortunately, I had an automated schedule set on Macrium Reflect, whereby it created a system image every week. When nothing worked, I used to revert to this image, and was able to use my Windows 10 installation that was, at most, a week old. …
… Related I use ChatGPT, Claude, Perplexity, and Gemini daily — here's the only one worth paying for One stands above the rest. GPT-OSS 20B Honorable mention No productivity piece would be complete without an honorable mention for the heavyweight in the room: GPT-OSS 20B. …
… Take my Paperless-GPT text extraction pipeline, for example. Since minicpm-v is a vision-capable model, it’s highly accurate at recognizing text in images and PDF documents. …
… Between the two, Qwen3 Coder Next wins on quality and gpt-oss-120b wins on speed. If you need a first draft in five minutes and plan to review it yourself, gpt-oss-120b is genuinely impressive. …
