visiondude

the starry night one is soo funny

so the architect of government bailout gets a cushy gig. probably one of the most harmful precedents set and now companies expect bailouts. to bailout the company instead of people and small shareholders was always poor decision, emboldened the worst of the business class. don’t love this hire lol

the way he could really be the spoiler king is to release an their training dataset to open source… doubt he’d go that far.

yeah i’ve been looking for online social spaces that have some sort of human verification to reduce my slop exposure. the PRSN app that launched recently seems promising but it’s empty rn.

although not perfect for other reasons, a captcha made using phone motion and device attestation like prsn.you is a more challenging bypass for today’s agent environments

did i miss it on the webpage or is the source prompt that was used to teach these models the game anywhere? i can see the soul artifacts on github but not the initial prompt and toolset definition. the prompt is perhaps the most important component in how a model would behave in a game. without reviewing the initial prompt used for the game the findings are unreliable since the prompt will vastly change how models play this game

while not scientific this is been my experience as well. i will add that language specificity in word choice is also a learned behavior. for example, the word “investigate” vs the phrase “look into”. You will find the outputs are quite different. can you guess which will use more tokens? it’s stuff like this that actually sets people apart in the top percentile of using these tools

My hypothesis is that headspace registered many user notifications and since user notifications trigger an app launch and perhaps you have optimize storage by offloading apps enabled? ios has a quirky app state where some local data exists but the app itself (ipa package) is offloaded

I very confused, couldn’t they have achieved much better outcome with existing hls tech with adaptive bitrate playlists? Seems they both created the problem and found a suboptimal solution.

“NYTimes fights blatant and obvious copyright infringement with legal processes to assess damage” - another angle.

Oh cool, can you share concrete examples of times codex out performed Claude Code? I’m my experience both tools needs to be carefully massaged with context to fulfill complex task.

I completely agree with this. The amount of unprompted “I used to love Claude Code but now…” content that follows the exact same pattern feels really off. All of these people post without any prompts for comparison, and OP even refused to share specifics so we have to take his claim as ‘trust me bro’

Ah bots analyzing bots. Seems openai has a larger bot army than Anthropic rn

Color palette generator: https://claude.ai/public/artifacts/719b00a3-66e7-46c7-b90d-a...

I like the use case for mini design exploration tools

It’s hard to tell when a turn starts if the tile stays on the same square. Could you possibly add a quick fade animation to the tile?

LMStudio works surprisingly well on M3 Ultra 64gb and 27b models.

Nice to have a local option, especially for some prompts.

^ seems like the way to go. open source and more features.

always seemed to me that efficient caching strategies could greatly reduce costs… wonder if they cooked up something new

They did!!! At least color options. Just announced at platform state of the union

Excited to try these out and see benchmarks. Expectations for on device small local model should be pretty low but let’s see if Apple cooked up any magic here.