I recreated Fable 5 with Opus and agent loops, and it's close enough that I stopped missing the banned model
…For the stuff you do over and over again, I'd rather use Opus 4.8 or even a cheaper model like GPT-5.5. Where Fable 5 really stood out was…
Search
Related topics:
GPT-5
Tracked topic
GPT-5
Top stories
I ran a full LLM on my phone with no internet, and it's more useful than I expected
…None of these tasks need flagship AI models like Opus 4.7 and GPT 5.4. More importantly, none of them need a server thousands of miles away to process your request…
Local LLMs are actually good now, and I wasted months not realizing it
…On the MMMU-Pro visual reasoning benchmark, Qwen3.5-9B scored 70.1, which is not far behind leading models like Gemini 3 Pro and GPT-5.4 that score in the…
I added one tool to my local LLM setup, and it finally stopped making things up
…My gpt-oss20B model ended up being more usable than expected, so I kept it in my rotations rather than discarding it as a side project. As powerful as local LLMs have…
I ditched Claude for Obsidian and a local LLM, and miss it less than I expected to
…was back when I was still a bit newer to local models and defaulted to gpt-oss20B. Now, I've been running better models such as Qwen 3.5 9B and Gemma…
I gave my gaming PC and phone the same local LLM tasks, and only one of them is still in my daily rotation
…My first ever local model was actually gpt-oss 20B, and I managed to get it running on 8GB because LM Studio has a GPU offload setting that splits the model between…
I stopped trusting cloud AI with my personal files, and switched to this local setup instead
…For reference, my primary local model is Qwen 3.5 9B , but I also still use gpt-oss 20B from time to time. The document handling is more capable than I expected…
I paid for Perplexity, Claude, and NotebookLM, and only one was worth keeping
…You get unlimited Pro Searches instead of being capped daily, access to bigger models like GPT-5, Claude Sonnet 4.6, and Gemini 3 Pro instead of being routed through whatever default…
I switched from Claude Code to Codex for a week, and the trade-offs surprised me
…02 / 8 AI Coding What underlying model powers OpenAI's Codex agent, distinguishing it technically from Claude Code's Anthropic-built foundation? A GPT-4 Turbo B o3 C Codex-001 D…
I stopped using Claude for coding, but now I can't live without it for everything else
…be making you faster. Another big reason is that the alternatives are genuinely good now. GPT-5.5 has caught up on coding in ways I didn't expect a year ago…