HackerTrans
TopNewTrendsCommentsPastAskShowJobs

beefsack

2,868 karmajoined il y a 14 ans
Programmer from Canberra, Australia.

Interested in remote Rust or Go jobs.

https://github.com/beefsack

comments

beefsack
·hier·discuss
I'd say Codex and Claude Code have different strengths and weaknesses. Claude Code is significantly better in terms of their subagent UI for example - being able to see the list of subagents under the input is great.

To be honest though, I've gotten to the point where I prefer the OpenCode UI. A big win for OpenAI is you can log in to your subscription in OpenCode, whereas this is not trivially achievable for a Claude subscription.

I was getting some really impressive cost efficiency today in OpenCode with the following:

  * Main session agent: gpt-5.6-sol (high) via OpenAI subscription
  * General purpose subagent: deepseek-v4-pro (high) via OpenCode Go subscription
  * Using `obra/superpowers` for subagent driven workflows
  * The main session only being allowed filesystem read permissions and everything else delegated
It was absolutely crunching through tasks without hitting the limit, and this combination is quite cost effective.

GPT 5.6 was picking up on quality and functional issues from DeepSeek and having it resolve them cleanly, and I didn't even get close to my quotas whereas I can usually blast through them. I feel as people get more comfortable with subagents and mixing and matching models in their daily work, Anthropic's walled garden stance will start to hurt them.
beefsack
·il y a 2 mois·discuss
I think it would be the case in many of the commonwealth countries. You hear "sorry" being used a lot like this in Australia too.
beefsack
·il y a 4 mois·discuss
I feel this would be more useful for tasks like "Check website X to see if there are any great deals today". Specifically, tasks that are loosely defined and require some form of intuition.
beefsack
·il y a 4 mois·discuss
The different bindings vs Vim was actually what stopped me using it. I really really wanted to love it and love a lot of the motivation and principles behind it, but unlearning decades of muscle memory is an absolute nightmare.
beefsack
·il y a 4 mois·discuss
Many people buy two separate Claude pro subscriptions and that makes the limit become a non-issue. It works surprisingly well when you tend to hit the 5 hourly limit after a few hours, and hit the weekly limit after 4-5 days. $40 vs $100 is significant for a lot of people.
beefsack
·il y a 5 mois·discuss
Prompting isn't programming. Prompting is managing.
beefsack
·il y a 5 mois·discuss
It almost always devolves into some all encompassing ERP that is meant to solve the needs of all parts of the business and save millions in licensing costs, and we all know how well that plan goes.
beefsack
·il y a 6 mois·discuss
I feel like so many of these memory solutions are incredibly over-engineered too.

You can work around a lot of the memory issues for large and complex tasks just by making the agent keep work logs. Critical context to keep throughout large pieces of work include decisions, conversations, investigations, plans and implementations - a normal developer should be tracking these and it's sensible to have the agent track them too in a way that survives compaction.
beefsack
·il y a 10 mois·discuss
The model is usually so confused after a /compact I also prefer a /clear.

I set up my directives to maintain a work log for all work that I do. I instruct Claude Code to maintain a full log of the conversation, all commands executed including results, all failures as well as successes, all learnings and discoveries, as well as a plan/task list including details of what's next. When context is getting full, I do a /clear and start the new session by re-reading the work log and it is able to jump right back into action without confusion.

Work logs are great because the context becomes portable - you can share it between different tools or engineers and can persist the context for reuse later if needed.
beefsack
·il y a 2 ans·discuss
Open the Terminal and type help to start a puzzle, not much to it but it was a bit of silly fun!
beefsack
·il y a 7 ans·discuss
Here's a specific example for a C++ compiler: CVE-2019-0546

I have a feeling you could find Java ones too if you looked hard enough. Compilers are complex beasts.

[1]: https://nvd.nist.gov/vuln/detail/CVE-2019-0546
beefsack
·il y a 8 ans·discuss
I'm in exactly the same boat, and ended up on Go Read, but recently I was looking for a solution which had better mobile support and came back to Feedly.

Created an account first and checked whether you can export your OPML, and indeed you can in the feed settings: https://i.imgur.com/ttPNrd1.png

The mobile app is great too, it has become my main RSS reading platform.