tmz Thomas @ithmzeth

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of

13K 26K 88K 92.1M 24K

0 0 1 79 0

View Details

tmz Thomas @ithmzeth

2 weeks ago

among the AI harnesses, I'd like CC worktree feature the most. it brings along .env to the worktree without needing to copy paste by hand, which is very annoying. and the worktree stays in the project local, not globally like others. damn, so good

0 0 0 24 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

no one talks about openclaw anymore

0 0 0 18 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

@Rasmic @theo gpt 5.5 or opus 4.8 couldn’t figure out your bugs but the point is, you also couldn’t figure out yourself? if you know the bug you can guide just deepseek to fix it lol or if youre non tech then forget what Ive said

0 0 0 357 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

@ay_ushr @going2hellstfu just three prompts for opus 4.8 to review codes and 25% usage is gone lol i wish it was weekly based usage

0 0 0 48 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

@aylleenx @hqmank piracy business ? im not sure but just go ahead and purchase plus plan on your own. that’s better option than piracy business if real business then I think Openai team solves real quick

1 0 0 32 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

@aylleenx @hqmank you’ll see monthly quota if you’re on free plan. They do this on purpose since OpenAI generously allows people to enjoy Codex. Some minorities abuse this. They have 5M active users on Codex, but I believe there are only 1M real users. 😂

1 0 0 58 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

@JustinGorya @hqmank Anthropic bans too haha.

1 0 1 38 0

View Details

tmz Thomas @ithmzeth

3 weeks ago

You can get access to Gemini 3.5 "fast mode" models inside @antigravity 2.0 for a limited time. GPT5.5/Opus4.6 for planning + Gemini 3.5 (Fast Mode) for implementation is a beast. Imho, opus4.6 is token efficient currently and perform slighty better at planning than opus4.8.