lkt

no profile record

·11 日前·議論

American politics often have a blast radius of the entire world, Swedish politics less so

·28 日前·議論

The guy running the twitter account is incompetent but the actual devs are a lot saner I think.

I agree it reflects poorly on them though

lkt

·先月·議論

Drew should include himself on that list, he’s earned it.

lkt

·2 か月前·議論

Is it cheap? `chat-latest` on https://developers.openai.com/api/docs/pricing is showing $5/$30 input/output which is the same price as gpt-5.5

lkt

·5 か月前·議論

Yes I have the "Google AI Pro" plan from here https://gemini.google/subscriptions/ and you can login to the Gemini CLI with oauth

lkt

·5 か月前·議論

Anyone know if this is available in the Gemini CLI with a subscription (not api key)? Still seeing only Gemini 3 pro preview

lkt

·5 か月前·議論

Is it AI generated though?

lkt

·7 か月前·議論

I've been doing some reverse engineering recently and have found Gemini 3 Pro to be the best model for that, surprisingly much better than Opus 4.5. Maybe it's time to give Codex a try

lkt

·7 か月前·議論

That's what I thought too, but the article says it was submitted to ZDI and they handled the communication with Posthog

lkt

·7 か月前·議論

Out of interest, how much does ZDI pay for a bug like this?

lkt

·7 か月前·議論

They do scan but they miss a lot. The frequency decreased after Github started scanning all repositories but I still report leaked secrets to bug bounty programs pretty often. Unfortunately Home Depot don't have a bug bounty program so I don't scan them.

lkt

·7 か月前·議論

No because it allows you to set the bozo bit on them and completely disregard anything they say in the future

コメント