HNHacker News
TopNewBestAskShowJobs

ZeroCool2u

4,020 karma · joined September 30, 2014

https://theolinnemann.com
submissionscomments
ZeroCool2u··on Launch HN: Vassar Robotics (YC X25) – $219 robot arm that learns new skills
Already sold out :( Any idea when the unassembled kits will be back in stock?
ZeroCool2u··on Cloud Run GPUs, now GA, makes running AI workloads easier for everyone
I think Cloud Run Functions would be the direct equivalent to Lambda.
ZeroCool2u··on Pyrefly vs. Ty: Comparing Python's two new Rust-based type checkers
Anyone reading this, if you're like me and prefer the open source version of VSCode where Microsoft disables Pylance, I'd encourage you to try BasedPyright instead.
ZeroCool2u··on Claude 4 System Card
In my experience with Gemini it definitely does not take a few minutes. I think that's a big difference between Claude and Gemini. I don't know exactly what Google is doing under the hood there, I don't think it's just quantization, but it's definitely much faster than Claude.

Caching a code base is tricky, because whenever you modify the code base, you're invalidating parts of the cache and due to conditional probability any changed tokens will change the results.

ZeroCool2u··on Show HN: Buckaroo – Data table UI for Notebooks
This looks really cool. I will say my default solution for this, and the default across my org, is Data Wrangler in VS Code[1]. My only wish list item is if the low code solution wrote polars instead of pandas. Any thoughts on how hard that might be to accomplish?

1: https://marketplace.visualstudio.com/items?itemName=ms-tools...

ZeroCool2u··on A Research Preview of Codex
"23 SWE-Bench Verified samples that were not runnable on our internal infrastructure were excluded."

What does that mean? Surely this should have a bit more elaboration. If you're just excluding a double digit number of tasks in the benchmark as uncompleted, that should be reflected in the scores.

ZeroCool2u··on Fed's Preferred Inflation Gauge Stalls While Spending Picks Up
Gift URL here since HN strips it: https://www.bloomberg.com/news/articles/2025-04-30/fed-s-pre...
ZeroCool2u··on Show HN: Memex is a Claude Code alternative built on Rust+Tauri for vibe coding
Oh wow okay, yeah big difference.
ZeroCool2u··on Show HN: Memex is a Claude Code alternative built on Rust+Tauri for vibe coding
How does it compare to just using Roo or Cline in VSCode?
ZeroCool2u··on Packing Input Frame Context in Next-Frame Prediction Models for Video Generation
Wow, the examples are fairly impressive and the resources used to create them are practically trivial. Seems like inference can be run on previous generation consumer hardware. I'd like to see throughput stats for inference on a 5090 too at some point.
ZeroCool2u··on GPT-4.1 in the API
No benchmark comparisons to other models, especially Gemini 2.5 Pro, is telling.
ZeroCool2u··on DolphinGemma: How Google AI is helping decode dolphin communication
Wow, there's a lot of cynicism in this thread, even for HN.

Regardless of whether or not it works perfectly, surely we can all relate to the childhood desire to 'speak' to animals at one point or another?

You can call it a waste of resources or someones desperate attempt at keeping their job if you want, but these are marine biologists. I imagine cross species communication would be a major achievement and seems like a worthwhile endeavor to me.

ZeroCool2u··on Google will let companies run Gemini models in their own data centers
FedRAMP High is the mark you really want to hit for the US Government and GCP's service coverage is surprisingly broad in that realm.
ZeroCool2u··on Claude's Max Plan
Yeah AI Studio is free with decent rate limits, though obviously more developer focused: https://aistudio.google.com/

The official Gemini app works well for me too and there's a nice free tier and it's free if you have a newer Pixel phone. Otherwise $20/month for the Advanced tier. There's no $200/month option.

https://gemini.google.com/app

ZeroCool2u··on Claude's Max Plan
I mean I've tried it with Gemini 2.5 Pro + Roo and then tried Claude 3.7 + Roo on the same task and Gemini blew Claude away. Haven't spent anymore OpenRouter credits, because Gemini was so much better.
ZeroCool2u··on Claude's Max Plan
Have you tried Roo Code or Cline instead? I never felt the need to use Cursor after trying them and they're just extensions, so it's easy to install and use your own API key.
ZeroCool2u··on Claude's Max Plan
I mean you get a 2 Million token context window and by far my favorite coding model with Gemini 2.5 Pro.
ZeroCool2u··on Mac Numbers now supports LAMBDA functions and MAP
Great question, but I'd probably have to try it to have a good answer!
ZeroCool2u··on Mac Numbers now supports LAMBDA functions and MAP
Just occurred to me that I've no idea what Numbers even looks like, because it's always been hard blocked on my corporate MacBook.
ZeroCool2u··on Amazon introduces Nova Chat, entering the arena with ChatGPT, Claude, Grok
I'm talking about the actual product interface here: https://nova.amazon.com/chat

Unless I've missed it, which is totally possible, I don't see anything in the UI or the settings that lets me change to a different theme.

ZeroCool2u··on Amazon introduces Nova Chat
Do they?? Trying to get GPU's from AWS at work is like pulling teeth for me.
ZeroCool2u··on Amazon introduces Nova Chat
The UI is kind of horrendous. Not even a dark mode. I also have a hard time imagining wanting to use BedRock at this point. Still can't use any of the leading models besides Claude, plus IAM config is comparatively painful, and you have to setup bedrock-access-gateway to get an OpenAI compatible API for tools that expect that API setup.
ZeroCool2u··on iPhone users can now set WhatsApp as their default calling and texting app
Would love to be able to do this, but with Signal.
ZeroCool2u··on Bloomberg: BYD's Five-Minute Charges Compare with Competitors (Gift Article)
Sorry, it seems like HN automatically stripped the URL to its base form, so the gift article pass doesn't work.
ZeroCool2u··on Gemma 3 Technical Report [pdf]
There's a big blue button on the top left that says "Get API key" and after you perform a prompt in the UI there's another button that says "Get code". Between those you should be good to go.
ZeroCool2u··on Show HN: We built Lovable for Mobile Apps (uses Flutter)
In Project IDX you can view Flutter Web previews as a tab in VS Code. Have you considered trying some variant of that?
ZeroCool2u··on Show HN: We built Lovable for Mobile Apps (uses Flutter)
This is very cool. I've been using Project IDX and the Roo AI extension to work on Flutter apps in YOLO mode and its been pretty cool. The only issue is the model can't interact with the Android Emulator preview. Still trying to figure out a workaround to that, but if anyone has any ideas would love to hear!
ZeroCool2u··on Gemma 3 Technical Report [pdf]
You can just go here: https://aistudio.google.com/prompts/new_chat

Select Gemma 3 from the drop down on the right side.

ZeroCool2u··on Fastplotlib: GPU-accelerated, fast, and interactive plotting library
Seems like a nice library, but I have a hard time seeing myself using it over plotly. The plotly express API is just so simple and easy. For example, here's the docs for the histogram plot: https://plotly.com/python/histograms/

This code gives you a fully interactive, and performant, histogram plot:

```python

import plotly.express as px df = px.data.tips() fig = px.histogram(df, x="total_bill") fig.show()

```

ZeroCool2u··on MacBook Air M4
Both work fine for charging, so seems like best of both worlds to me.
← PreviousPage 5 of 25Next →