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

I did this with github actions + opencode. It has mainly two components called daydream and nightwatch. Daydream runs on a daily schedule looking at the VISION.MD file in the project and also look at the project and suggest new ideas, security , maintenance tasks (you can set a ratio of maintenance vs new ideas) and create a new issue. Then nightwatch runs daily at night and picks up oldest issue and suggest a PR. I'm in total control of merging, can ask for changes which agent again will execute immediately.

This has been helpful to revive few old projects and keep momentum on active projects. I've been closing more PRs than merging but I think that's fine. I quickly ran out of free github action hours so I had to self host actions. However basic self-host actions setup may not be secure enough because VM is not destroyed after each action like github own action jobs environment.

Anybody can try it out actions from https://github.com/chamoda/agent-foundry, minimal setup don't need any API keys, works with mimo 2.5 free model by default.


For anyone interested, here’s how I achieve the same in i3wm: it works with the Print key and lets you select the area using only CLI tools.

bindsym --release Print exec "scrot -s '%Y:%m:%d:%H:%M:%S.png' -e 'xclip -selection clipboard -t image/png -i $f && mv $f ~/Pictures'"


Well, you can even block event loop in `async def` if you are not careful. When you are using `async def` you need to do all your IO (disk, network) operations asynchronously or your are blocking the event loop.



Comments moved thither. Thanks!


Notable changes.

- The Bcachefs file system is now in the kernel

  Bcachefs is a next-generation of CoW (Copy-on-Write) file system for Linux (similar to zfs or btrfs with improvements). It has support for snapshots, compression, encryption, caching, replication and more.
- New Futex API

  Futex (Fast User-space Mutex) is kernel system call operate directly on user-space to improve performance of locking mechanisms inside programs. Set of significant incremental improvements made to clean up the Futex API.
- Exceptions for BPF virtual machine

  Did you know that there's a virtual machine called BPF that runs inside kernal space to safely execute dynamic programs with JIT compilations? BPF (Berkeley packet filter) has been getting more and more improvements over the years and exceptions was the latest improvement to the language.
- Itanium (IA-64) architecture removed for the kernel

  IA-64 which was Intel's attempt for 64 bit processor architecture which was completely overshadowed by AMD's x86-64 is now completely gone from the Linux kernel.



As of now Bard is powered by Gemini Pro.

https://bard.google.com/updates


Okay, from my end, I am still seeing Palm (EU).


Same here, Google's offering is very weird though, a simple question to Bard about what it's using also outputs the wrong result. https://imgur.com/Vb1STQe


Ah, but can you tell which part of the result is wrong? Maybe a follow up question to the LLM?


Gemini is not available in the EU is it?


> Just as for Bard, Europe will need to wait for Gemini

https://thenextweb.com/news/google-gemini-ai-unavailable-eur...


When they finally release this train wreck to the EU we will have had another round of OpenAI, Antrophic and finally Mistral releases. Why even pretend to compete Google? Just admit already that you guys are only interested in shoving ads in our faces and call it a day?


In my language/country I see no mention of Gemini there. Or any model name, really.


Free quota looks reasonable with 60 queries per minute. On the other hand data from free quota requests will be used to improve the product.

https://ai.google.dev/pricing


It’s far more than reasonable, it might be Google’s saving grace.

I wasn’t going to bother even testing Google’s AI products unless everyone started gushing about how much better they are than GPT4 but with 60 free queries per minute? That’s worth exploring even if only to find out shortly that it’s not worth paying for.


Typical Google behavior, where it's cheap/free in the beginning, and when you've built on top of it prices increases drastically? Like gmaps pricing.


This must be a significant investment to pick up the hype; 1 qps cannot be sustainable with a free pricing tier unless their resource efficiency is 10x better than competitors.


No doubt it’s a loss leader to some degree but, in practice, very, very few customers will have sustained request rates of 60 requests per minute. Their actual usage averaged across all users will be a tiny fraction of that.

For users that get close to that sustained rate, they’re just as likely to exceed it and actually pay.



It's look like they use next.js in the generated website but they don't let you at least download the source code for further modifications.


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

Search: