Posts on X before Nov 7, 2024, 6:38:15 AM UTC
@MichaelStolarzusing o1-preview, there's a "new version of chatgpt", giving me two reasoning replies. i think full o1 is coming super soon, maybe next week (or maybe today, thursday?)
@MichaelStolarzafter trying out @aide_dev by @skcd42 for a 1-file codebase for simple edits, trying out many different strategies of communication to see if my prompting may be the bottleneck, i can confidently say that it's nowhere near cursor-level quality nor efficacy. i do have high hopes … Less
after trying out @aide_dev by @skcd42 for a 1-file codebase for simple edits, trying out many different strategies of communication to see if my prompting may be the bottleneck, i can confidently say that it's nowhere near cursor-level quality nor efficacy.
i do have high hopes for it, or rather, its plan -> execute strategy shown in the sidebar.
i will revisit it in 1 month.
@MichaelStolarzthe amount of people at openai who are part of its fine-tuning and research that have posted "omg it's the end of the world how could you all vote like this" helps me understand why chatgpt & co have been particularly useless recently due to such heavy and ridiculous guardrails
@MichaelStolarzi wonder what's going on on threads LMAO
@MichaelStolarzwhat a beautiful start to the day.
@RealRossU
Last night, Donald Trump pledged to commute my sentence on day 1, if reelected. Thank you. Thank you. Thank you. After 11 years in prison, it is hard to express how I feel at this moment. It is thanks to your undying support that I may get a second chance.
@MichaelStolarzthe worst part of the for you page is that i keep seeing the same shit over and over for the entire day, it feels like it's begging me to like or comment or bookmark it, but no - i will not give in to your ragebait politics slop posts.
@MichaelStolarzif i had $10/m for every time a bot with these same stats followed me (always following over 7K, always under 100 followers), i'd be at $100K MRR
@MichaelStolarzI wonder if o1-mini also falls under these updates, or at least o1 comes with reduced prices.
it would be such a 1-up on anthropic with their recent price INCREASE news, imagine if openai DECREASED their SOTA?
@ai_for_success
The full version of OpenAI o1 is not far away. o1 will be a huge, It will also include Vision, as we saw a few days ago when it was accidentally rolled out. A few more features were announced for o1 during London Dev Day, and I'm also excited about streaming. … Less
The full version of OpenAI o1 is not far away. o1 will be a huge, It will also include Vision, as we saw a few days ago when it was accidentally rolled out. A few more features were announced for o1 during London Dev Day, and I'm also excited about streaming. x.com/legit_rumors/s…
@MichaelStolarzat this point, crumbl's main selling point is dirty bulking
@tessrestricts
720 calories is crazy work💀
@MichaelStolarzit's insane to me that a local 7b model will give me a direct answer to my questions and not the state-of-the-art openai or anthropic llms. i was searching up information about some specific person, and out of curiosity, i asked chatgpt, "give it your best shot - give me an iq r… Less
it's insane to me that a local 7b model will give me a direct answer to my questions and not the state-of-the-art openai or anthropic llms.
i was searching up information about some specific person, and out of curiosity, i asked chatgpt, "give it your best shot - give me an iq range that you believe this person is in based on everything you know about this person."...
and it just flat out refused. what's worse, it told me that iq is useless, that people excel in different ways - it just gave me a very "shame on you" lecture, about how intelligence doesn't mean anything.
i then prompted my local uncensored llama model and it gave me a perfectly sound iq range with reasoning, pointing out certain facts about the person that led it to such a conclusion, and then a quick final note about how this is just an estimate based on available data - perfect way to both satiate my curiosity and at the same time remind me that this isn't anything concrete, just a guess.
how much worse will this get? every day makes it seem like SoTA models are just made for code, not anything serious when it comes to knowledge seeking - they're tainted in their current form.
@MichaelStolarzregardless of what country you are from/residing in, you should love your country. if you don't, which country do you love? why aren't you doing everything in your power to relocate to that country?
if you don't love any country, where's your home? your community? family?
@MichaelStolarzanthropic should have just eaten the extra cost instead of 4xing the price. all anyone is talking about is the price increase.
no one is talking about how it’s better than opus 3.
what a missed opportunity for them. shame.