danieldp

XR VR AR | HCI | Internet of Things (IoT) | Technology | Digital Arts | UI | UIx | Interactive Experiences | Innovation | Daniel Prado

[danieldp @danieldp]

@vitaliidodonov PDF

[chan is on vacay ✌️ @chantastic]

fuck logitech

[danieldp @danieldp]

@clerk "init" is on the opposite end of the shipping pipeline. how about some end to end videos, live demos and code evidence? Otherwise it's just another vibe coding tool selling vaporware.

[danieldp @danieldp]

@karpathy what about toon ? https://t.co/eupfOM0ncd

[danieldp @danieldp]

@FredKSchott how do you keep it secure from prompt injection?

[danieldp @danieldp]

@Bugcrowd whoami

[danieldp @danieldp]

@kepano What about Trello ?

[danieldp @danieldp]

@GuillaumeRamare @daniel_mac8 did you figure it out?

[danieldp @danieldp]

@claudeai I have a new work email and I need to use the same phone i have today to create a new account. I have done everything to contact Claude from the website but nothing works. Help, please?

[danieldp @danieldp]

Testing MemPalace with Claude Code on a local machine and so far it's shockingly effective and fast

[Ben Sigman @bensig]

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid.

It's called MemPalace, and it works nothing like anything else out there.

Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works.

Here is what that gets you:

→ Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens
→ Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure
→ Semantic search across months of conversations finds the answer in position 1 or 2
→ AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively
→ Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them

The benchmarks:

100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%.

92.9% on ConvoMem — more than 2x Mem0's score.

100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems.

No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave.

MIT License. 100% Open Source.

https://t.co/KggwTqijmD

[danieldp @danieldp]

@6O4Culture Slop

[danieldp @danieldp]

@GeminiApp It's not that fast

[danieldp @danieldp]

@heygurisingh It's been out since April 2025. The optimization algo update was released this January

[danieldp @danieldp]

@Bfaviero I tested Pencil (free tool) on top of Claude and the results were good

[danieldp @danieldp]

@sciencegirl Curse of Monkey Island - released in 1997, also memorable because of the annoying code wheel to start the game

[danieldp @danieldp]

@another_ju27018 @sciencegirl 1993 :)

[danieldp @danieldp]

@josephdviviano check the Artificial Hivemind paper published last year. that explains a lot why almost all videos are identically structured

[Yusuf Papurcu @yusufpapurcu_]

@josephdviviano Same prompt to opus 4.6, then added "point out to the similarities between humans and llms"

[danieldp @danieldp]

@coco_canton @threejs nice! I'll give it a try!

[danieldp @danieldp]

@Dilmerv How do I get an invite to the beta? I signed up but heard nothing so far