HNHacker News
TopNewBestAskShowJobs

diwank

2,120 karma · joined September 11, 2011

Dropped out of Columbia (physics, philosophy) for a Thiel Fellowship. Built Julep AI — open-source AI agent framework, 7k stars on GitHub — because I wanted agents that could actually do things. Now building Memory Store (YC X26): persistent memory for AI agents. Turns out the hard problem isn’t making agents smart, it’s making them remember.

Still fascinated by what foundational models and cognitive architectures teach us about our own minds. Building beats theorizing, but sometimes they’re the same thing.

https://memory.store

https://diwank.space

hi@diwank.space

submissionscomments

Left Brain, Right Brain: Facts and Fantasies

pmc.ncbi.nlm.nih.gov·3 pts·diwank·
0

A gas-enshrouded and gas-reddened black hole at cosmic dawn

nature.com·4 pts·diwank·
0

Ask HN: Which is the least sloppy and claudeism free model you have used?

4 pts·diwank·
0

Anthropic releases Claude Fable 5

theverge.com·4 pts·diwank·
0

Sonny Rollins Is Dead

nytimes.com·1 pts·diwank·
0

Breakthrough Prize Announces 2026 Laureates

breakthroughprize.org·3 pts·diwank·
0

Reasoning models encode tool choices before they start reasoning

arxiv.org·3 pts·diwank·
0

Show HN: Datetime-bench: which datetime formats LLMs get right (and wrong)

github.com·2 pts·diwank·
1

Show HN: Dropbox for Your Agents' Memories

memory.store·2 pts·diwank·
0

Show HN: IQT – Why space feels panoramic and time feels fleeting

github.com·1 pts·diwank·
0

Putting Gemini to Work in Chrome

blog.google·56 pts·diwank·
63

From kinetic gases to an exponentially expanding universe

iopscience.iop.org·1 pts·diwank·
0

DeepSeek-v3.2 and v3.2 Speciale Announced

huggingface.co·5 pts·diwank·
0

Effective harnesses for long-running agents

anthropic.com·125 pts·diwank·
37

Cursor 2.0 – A step in the wrong direction

forum.cursor.com·3 pts·diwank·
1

Stress-testing model specs reveals character differences among language models

alignment.anthropic.com·2 pts·diwank·
1

Thinking Sparks: Emergent Attention Heads in Reasoning Models

arxiv.org·1 pts·diwank·
0

The contextvars and the chain of asyncio tasks in Python

valarmorghulis.io·2 pts·diwank·
0

AI Village: Watch frontier AIs interact with each other and the world

theaidigest.org·3 pts·diwank·
0

Discovery of Unstable Singularities in Navier Stokes (DeepMind)

arxiv.org·2 pts·diwank·
0

Llama.cpp: Deterministic Inference Mode (CUDA): RMSNorm, MatMul, Attention

github.com·6 pts·diwank·
0

New Ways to Use NotebookLM

blog.google·4 pts·diwank·
0

Veo 3 and Veo 3 Fast – new pricing, new configurations and better resolution

developers.googleblog.com·2 pts·diwank·
0

Using AI to perceive the universe in greater depth

deepmind.google·55 pts·diwank·
23

The Himalayan village where you can see the cosmos

bbc.com·3 pts·diwank·
0

Beyond the terminal: Gemini CLI comes to Zed

developers.googleblog.com·3 pts·diwank·
0

Principal–Agent Problem

en.wikipedia.org·2 pts·diwank·
0

Codestral 25.08 and the Mistral Coding Stack

mistral.ai·1 pts·diwank·
0

Phi-Ground: Advancing Perception in GUI Grounding

zhangmiaosen2000.github.io·2 pts·diwank·
0

Voyage-context-3: focused chunk-level details with document context

blog.voyageai.com·2 pts·diwank·
0
Page 1 of 8Next →