HackerTrans
TopNewTrendsCommentsPastAskShowJobs

simonpure

15,281 karmajoined 13 years ago
strong advocate of languages using parenthesis, tech backed by RFCs, and challenging the status quo.

currently working on transflux: agent driven development for clojure(script).

Submissions

Litert.js, Google's High Performance Web AI Inference

developers.googleblog.com
1 points·by simonpure·2 hours ago·0 comments

Computation as a universal and fundamental concept

ergo.org
158 points·by simonpure·yesterday·131 comments

SensorFM: Towards a general intelligence and interface for wearable health data

research.google
2 points·by simonpure·2 days ago·0 comments

Native-speed vLLM transformers modeling back end

huggingface.co
3 points·by simonpure·3 days ago·0 comments

Pre-fitted Jacobian Lenses for specific models

huggingface.co
1 points·by simonpure·4 days ago·0 comments

Kernels: Major Updates

huggingface.co
5 points·by simonpure·5 days ago·0 comments

Tau: A minimalist agent that teaches you to create coding agents

github.com
4 points·by simonpure·5 days ago·0 comments

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

arxiv.org
53 points·by simonpure·8 days ago·9 comments

U.S. Department of Energy Delivers Third Advanced Reactor Criticality

energy.gov
8 points·by simonpure·9 days ago·0 comments

China's Great Green Wall: 66B trees growing faster than natural forests

livescience.com
9 points·by simonpure·11 days ago·0 comments

CachyOS June 2026 Release

cachyos.org
142 points·by simonpure·12 days ago·78 comments

Cornell Recovered $100k in Unidentified Payments with AI

innovationhub.ai.cornell.edu
5 points·by simonpure·16 days ago·0 comments

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

github.com
3 points·by simonpure·16 days ago·0 comments

Google's Gemini 3.5 Pro Release Slips to July

businessinsider.com
9 points·by simonpure·17 days ago·1 comments

World Action Models: A Survey

arxiv.org
4 points·by simonpure·17 days ago·0 comments

GDM: When AI agents meet [video]

youtube.com
1 points·by simonpure·18 days ago·0 comments

Forkd: Fork() for AI Agent MicroVMs

github.com
2 points·by simonpure·18 days ago·0 comments

SpaceX sheds $400B in market value as debut rally hits reverse

ft.com
77 points·by simonpure·19 days ago·95 comments

Software Engineers Face an AI 'Identity Crisis,' VC Partner Says

businessinsider.com
2 points·by simonpure·19 days ago·2 comments

Billionaire Tax Officially Heads to Nov. 3 Ballot

sos.ca.gov
45 points·by simonpure·20 days ago·63 comments

comments

simonpure
·2 days ago·discuss
There's a truly decentralized alternative to MLS:

Key Agreement for Decentralized Secure Group Messaging with Strong Security Guarantees [0]

[0] https://eprint.iacr.org/2020/1281
simonpure
·13 days ago·discuss
The readme was recently updated.

> In regard to AI usage, my fuzzing workflow was automated by AI with a strict harness. I used GPT-5.5-3-Codex-Spark for ALL the fuzzing, as barely any "thought" is necessary when provided with an efficient harness. Contrary to the growing narrative that I'm just some random child burning tokens, I DO actually have a degree in the subject and have published multiple papers on fuzzing methodology. I spent years researching and developing new tools and ideas for how to fuzz. You do NOT need a SOTA model to help you identify these issues, I promise!
simonpure
·16 days ago·discuss
Hug of death

` /api/hn -> 504 An error occurred with your deployment FUNCTION_INVOCATION_TIMEOUT cle1::c8vgv-1782399959042-aeba3cae05ff `
simonpure
·2 months ago·discuss
And the video version -

https://youtu.be/K1dBf40waNk
simonpure
·2 months ago·discuss
Thanks! I've noticed a big jump when they switched to Gemini 3.1 Pro and it really became useful. I like that I can use it from my phone too. It took a bit of trial and error but I came up with a good ralph loop between GitHub Actions and Google Jules using the Jules API. So basically I have Jules extend its TODO.md with the next set of tasks and open a PR then run a GitHub Action with a few checks, auto-merge, and then call back into Jules to kick off the next cycle if there are still open tasks. It then mostly just runs and occasionally gets hang up on some questions that I then answer on my phone mostly just telling it to make a judgement call and keep the build green. You can check out the prompt, action, and past PRs for examples ex. Jules prompt is here: https://github.com/alpeware/datachannel-clj/blob/main/prompt...
simonpure
·2 months ago·discuss
I've been working on a pure Clojure implementation of WebRTC Data Channels (SCTP over DTLS over UDP). The library provides a minimal, dependency-free (except for Clojure itself) way to establish peer-to-peer data channels on the JVM.

I've always wanted this and have used it to experiment with Gemini's cloud agent Google Jules.

https://github.com/alpeware/datachannel-clj
simonpure
·2 months ago·discuss
I was wondering the same and learned the model doesn't know about itself during training [0]

[0] https://developers.googleblog.com/closing-the-knowledge-gap-...
simonpure
·4 months ago·discuss
I've been impressed by Google Jules since the Gemini 3.1 Pro update. Sometimes it's been working on a task for 4h. I've now put it in a ralph loop using a Github Action to call itself and auto merge PRs after the linter, formatter and tests pass. It does still occasionally want my approval, but most of the time I just say Sounds great!

It's currently burning through the TESTING.md backlog: https://github.com/alpeware/datachannel-clj
simonpure
·8 months ago·discuss
There's DolphinGemma; no microchips needed -

https://blog.google/technology/ai/dolphingemma/