Hacker Newsnew | past | comments | ask | show | jobs | submit | jboss10's commentslogin

This model is on the pareto frontier, by Artificial Analysis' benchmarks.

https://artificialanalysis.ai/?cost=intelligence-vs-cost-per...


Sad this isn't about keyboards.

not exactly keyboards, but a lot closer then Deno's dacytl

https://github.com/kjloveless/dacytl

funny enough i wrote this years ago using Deno!


From here, it looks like opencode is hemorrhaging money. I've got a Opencode Zen free account, and I've been using deepseek-v4-flash-free on Pi for a bit, and I haven't hit a limit yet. Sometimes my request fails, but retrys work. I know this is a very cheap model, but it's being given out for free. I assume they might be training on outputs?


> Gemini 4 helped with the editing.

Does this guy have access to Gemini 4 already?

I'm guessing Gemma 4 was happy to be mistaken for Gemini and didn't catch this mistake.


“Helping” is doing some heavy lifting in that sentence! It appears to be 100% AI.


I couldn't get through it.

I find it exhausting trying to read anything that smells remotely like linkedin AI slop at this point.


Yes correct, Gemma. Will correct it shortly.


If you wrote an initial draft you should consider using a better model or just posting what you wrote.

The smaller models can be sufficient for coding but for document writing not highly specific I've yet to be satisfied with AI output. I certainly wouldn't expect gemma to produce good outputs.


Makes sense, perhaps I'll post the raw notes + more material with the next article, prior to any edit. I like to use local models, even if they are not that powerful precisely because of that, I'm forced to put in more thought and it's my signed off article in the end.

Thank you for the suggestion.


You don't build credibility by putting out slop and correcting it every time someone points out that it's wrong. You think it's our job to proofread and fact-check?


A genuine mistake. I make these posts for myself, mainly to structure & share my thoughts. Let me know if you find other errors, I appreciate the feedback.


How does it run the LLMs? Or does it call a API to llama.cpp/ollama/etc. ?

During normal usage, how often does it try to parse info from the screen capture? Once a minute?


You can decide which AI provider you use, either local through Ollama for example, using your own cloud API key, or using Screenpipe cloud. We also support confidential inference through tinfoil.sh

Screenpipe captures accessibility tree and screenshot when you perform a meaningful action. It doesn't use AI at recording time (except PII removal and OCR infrequently). So it can be every few hundred milliseconds to few minutes or more (if screen idle or sleeping)

We usually benchmark CPU usage on $200 Windows/MacOS laptop


Michael Stevens (of Vsause fame) copies long quotes into notebooks, and he claims the act of writing it helps him remember. And if it's not worth writing, it's not a good enough quote.


Those are called commonplace books.



I use this setup as well. I've written an alias for bwrap which only gives the agent access to the current directory and read only access to the docs.

It has read-only access to my binaries, and I worry which programs I have might be a fingerprinting issue. I've thought about mounting a alternate /bin which using a docker image. (docker export)

Have you managed to setup any firewall or protection for the API keys? I know this is out-of-scope for bwrap.

edit: Maybe https://github.com/rootless-containers/slirp4netns could work


I think this is one of the easiest to understand.

https://arena.ai/leaderboard/text/pareto


That’s a good visualization, although I am a bit mistrustful of Arena’s scores. It does get around the fact that models are getting trained for the benchmarks, but the methodology of letting random people compare outputs side-by-side is a very shallow judgement method in my opinion.

EDIT: Indeed looking at the overall rankings for text again, the list is rather strange, a lot more about writing style than intelligence.


They supposedly have a style control system, but I doubt it's perfect. I wish there was a parento view like this for agentic systems(using a standard harness)


The second point is funny. I don't think not using air conditioning due to energy use is why Europeans don't have AC. (I'm European). It's beacuse it's expensive and difficult to retrofit. And we are getting more AC, lots of new buildings have it.

I agree with the article that Europeans should install more AC and that worrying about climate change isn't a valid reason not to. But this isn't because I don't beleve in climate change, it's because I don't agree with the idea of a climate footprint, and that people should worry about their own energy usage. They should worry about energy generation and green energy policy.

The rest of the article is either racist or ridiculous.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: