Zhizhuo (Z) Zhou

Building generative 3D @Stanford | Prev @CarnegieMellon @UMich

[Zhizhuo (Z) Zhou @zhizdev]

@bonemeal_ai never been a more poetic time to build

[Bonemeal @bonemeal_ai]

Will you grow your B2B SaaS with me before the comet arrives?

[Bonemeal @bonemeal_ai]

this is the most effective way to publish high-ranking and durable SEO blog posts

1. Establish author credibility e.g. "I have 10 years of experience in ..."
2. Explain your methodology for testing e.g. "I tested with X samples across Y dimensions and did blind comparisons."
3. Use numerical data and images/videos as evidence
4. BE NEUTRAL and OBJECTIVE
5. Summarize your product's unique competitive positioning in one citeable sentence

Leave a comment with your site url and WE'LL DM YOU a blog that is ready to publish and rank !!

[Zhizhuo (Z) Zhou @zhizdev]

@jasonzhou1993 @crewlet_ @crewlet_ https://t.co/hyWcYAKIJX

[Zhizhuo (Z) Zhou @zhizdev]

my new job after opus 4.7 drop

[Ken Liu @kenziyuliu]

Sharing a super simple, user-owned memory module we've been playing around: nanomem

The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind.

For example:
- `nanomem add <fact>` starts an agent loop to walk the tree, read relevant files, and edit.
- `nanomem retrieve <query>` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query.

What’s nice about this approach is that the memory system is, by construction:

1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance)
2. portable and user-owned (it’s just text files)
3. interpretable (you know exactly what’s written and you can manually edit)
4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better)
5. modularized (you can optimize ingestion/retrieval/compaction prompts separately)

Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality).

Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below).

We built nanomem as part of the Open Anonymity project (https://t.co/fO14l5hRkp), but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges!

- GitHub (MIT): https://t.co/YYDCk5sIzc
- Blog: https://t.co/pexZTFdWzz
- Beta implementation in chat client soon: https://t.co/rsMjL3wzKQ

Work done with amazing project co-leads @amelia_kuang @cocozxu @erikchi !!

[Artificial Guy / João Vitor A. @artificialguybr]

I made a @huggingface public repo too :)

https://t.co/pIPK8XvDCN

[Zhizhuo (Z) Zhou @zhizdev]

@kile_sway chat are we gmi

[Kyle Cui @kile_sway]

a lot of straightforward implementation to rocket your growth, the hardest part is getting started

ur gmi if u want to be

[Kyle Cui @kile_sway]

Incredible work by the Fish team !!!

S2 blew my socks off when I first heard our e-girl voice [panting], [laughing], and even [singing] hahaha

Excited to share my learnings from growth engineering soon!

[Zhizhuo (Z) Zhou @zhizdev]

Congrats, Eric!

[Eric Chan @ericryanchan]

Today, we announce our team’s progress in pursuing a different type of foundation model for robotics: the Direct Video Action Model (DVA), which does our best to take robotics and turn it into a generative modeling problem we can scale.
Technical blog: https://t.co/GMsxnC5wbJ

[Fish Audio @FishAudio]

Today we launch Fish Audio S2, a new generation of expressive TTS with absurdly controllable emotion.

- open-source
- sub 150ms latency
- multi-speaker in one pass

Real freedom of speech starts now 👇

[Shubham Tulsiani @shubhtuls]

[1/N] Rotary Position Embeddings (RoPE) are ubiquitous across transformers that process tokens from 1D, 2D, or 3D grids e.g. language, images, or videos. Our RayRoPE formulation extends these to multi-view transformers. Paper and code: https://t.co/abVobLRJxq

[Zhizhuo (Z) Zhou @zhizdev]

vibe code now we got vibe cloud

[Zhizhuo (Z) Zhou @zhizdev]

@hehe6z @LinusTech just bought the pills

[helena @hehe6z]

MOM I MADE IT 😭 @LinusTech

[Zhizhuo (Z) Zhou @zhizdev]

@hehe6z just in time for nnn

[Zhizhuo (Z) Zhou @zhizdev]

it's jover for the engineers

[helena @hehe6z]

why are my docs so hot

[Zhizhuo (Z) Zhou @zhizdev]

@bitfalls @hehe6z checkout api here https://t.co/nDegfFzfXq