Viewing profile — mnk47

In my experience, the model's performance in silly tasks like these is usually (not always) correlated with its performance in other areas except tool use/agent stuff.

You can just use the official Claude Code, OpenAI Codex, and Gemini extensions on VS Code. You get diffs just like in Cursor now. The performance of these models can vary wildly de…

Go is still going strong after 15 years. Dart, the language of Flutter, is 13 years old.

> In Obsidian, open the daily file amd copy the contents from yesterday What's the point of this? Isn't it easier to just keep reusing the same note?

Did you read the article? All it basically says is that OpenAI faced struggles this past year -- specifically with GPT-5 aka Orion. And now they have o3, and other labs have made h…

> So LLMs finally hit the wall Not really. Throwing a bunch of unfiltered garbage at the pretraining dataset, throwing in RLHF of questionable quality during post-training, and oth…

>Then there is the matter of actually defining general intelligence. It may also be the definition of consciousness, or at least require it. But currently, there is no mutually agr…

Announcement on X: https://x.com/FishAudio/status/1853655232779313408 Demo: https://huggingface.co/spaces/fishaudio/fish-agent Repo: https://github.com/fishaudio/fish-speech Weight…

Repo: https://github.com/Standard-Intelligence/hertz-dev

Sam Altman just replied: https://x.com/sama/status/1849661093083480123 > fake news out of control

> it is absurd to expect something to keep increasing forever just because it did increase for a short duration previously The problem isn't that it stopped increasing. It's that i…

Am I misremembering or is this an exact plot point of Pluto (the manga/anime)?

> yep, we want the same thing here. we want to be minorities in our own cities where in Western Europe is this currently happening? Which cities?

I wish trends like the Flynn effect (rise in IQ in most of the world throughout the 20th century, including China [0], Japan and Korea [1]) had more concrete answers by now. AFAIK …

By Meta FAIR, UC Berkeley and NYU X thread by one of the authors: https://x.com/jaseweston/status/1846011492245672043

> LLMs do not generate new content, they just shuffle old content together in new ways You can say the same thing about most technical books. They're quite often little more than a…

edit: They've added a cookbook article at https://cookbook.openai.com/examples/orchestrating_agents It's MIT licensed.