Hacker News: visiondude

New comment by visiondude in "Any Human Ever – One life, drawn at random from all who have ever lived"

visiondude — Thu, 03 Sep 2026 17:40:05 +0000

“He was born and died at 1 of dysentery.“ - lucky me

New comment by visiondude in "Show HN: Huzzah – a novel approach to coding with AI"

visiondude — Thu, 20 Aug 2026 20:36:32 +0000

not sure if the hz file artifact is needed, you can enter pseudocode directly into chat or even on an existing code file and with minor comment agents will be able to work with it. i write this type of pseudocode to existing code files often to great results.

New comment by visiondude in "Anthropic Risk August 2026 [pdf]"

visiondude — Fri, 14 Aug 2026 20:42:00 +0000

a mystery “model 2” is mentioned alongside mythos/fable.

New comment by visiondude in "How Claude's text watermarking works"

visiondude — Fri, 14 Aug 2026 20:04:23 +0000

I’d like to better understand the minimum text length to get a confident result, i would presume it would need to be quite long, perhaps > 1000 words to get an accurate result.

New comment by visiondude in "Lost my phone at the office. Claude suggested tracking Bluetooth signal strength"

visiondude — Fri, 07 Aug 2026 23:32:45 +0000

cool, that’s like the Phone Buddy app for Apple Watch

New comment by visiondude in "Zed DeltaDB"

visiondude — Wed, 05 Aug 2026 19:38:31 +0000

i think a system that uses git and file system artifacts (txt/md/xml files whatever preference) is much better. eng teams need to define their artifacts, eg plan file, reqs etc whatever is needed and important to that team. the agent convo itself doesn’t add much value IMO and adds unnecessary bloat.

New comment by visiondude in "Advancing the price-performance frontier with GPT‑5.6"

visiondude — Thu, 30 Jul 2026 18:36:28 +0000

there is a ton of downward price pressure from Chinese open weight models

New comment by visiondude in "Be skeptical of OpenAI's rogue hacker agent story"

visiondude — Fri, 24 Jul 2026 17:19:12 +0000

yeah the way the agent “escaped” their sandbox was always a bit off, seemed a bit too easy and surprised they didn’t have instrumentation to catch an non whitelisted network request. still demonstrates the capability though.

New comment by visiondude in "Claude Opus 5"

visiondude — Fri, 24 Jul 2026 17:16:04 +0000

The signal here is tokeneconomics are very real, price vs performance is starting to be a consideration even at the bleeding edge labs. maybe a subtle indication scaling is not all that is needed since if AGI was around the corner leading labs would still be incentivized to pour all resources into larger (smarter - or maybe not?) models

New comment by visiondude in ""Drawing" the Mona Lisa with GPT-5.6, Claude, Gemini, and Grok"

visiondude — Wed, 22 Jul 2026 00:32:25 +0000

the starry night one is soo funny

New comment by visiondude in "Ben Bernanke Joins Anthropic Oversight Trust"

visiondude — Fri, 10 Jul 2026 04:22:18 +0000

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

New comment by visiondude in "Muse Spark 1.1"

visiondude — Thu, 09 Jul 2026 21:02:51 +0000

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.

New comment by visiondude in "AI content is everywhere on social media, especially LinkedIn"

visiondude — Thu, 09 Jul 2026 20:59:42 +0000

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.

New comment by visiondude in "The CAPTCHA arms race: from distorted text to browser identity"

visiondude — Wed, 24 Jun 2026 17:40:19 +0000

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

New comment by visiondude in "A robot is sprinting towards you. Do you want it running on Claude or Grok?"

visiondude — Thu, 18 Jun 2026 07:07:46 +0000

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

New comment by visiondude in "Local Qwen isn't a worse Opus, it's a different tool"

visiondude — Thu, 18 Jun 2026 06:40:12 +0000

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

New comment by visiondude in "Tell HN: An app is silently installing itself on my iPhone every day"

visiondude — Sun, 26 Apr 2026 07:02:07 +0000

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

New comment by visiondude in "We replaced H.264 streaming with JPEG screenshots (and it worked better)"

visiondude — Tue, 23 Dec 2025 21:31:37 +0000

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.

New comment by visiondude in "Fighting the New York Times' invasion of user privacy"

visiondude — Wed, 12 Nov 2025 18:58:59 +0000

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

New comment by visiondude in "Claude Code on the web"

visiondude — Tue, 21 Oct 2025 02:46:42 +0000

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.