beefsack
beefsack on Hacker News
The unfortunate reality is that all of the fun recompilation projects are helping seal the fate of us not being able to run games, or software in general, on our own hardware. The risk is very quickly becoming too great for proprietary software publishers in letting compiled artifacts land in customers' hands.
I feel GTA 6 will be the last mainline GTA that we run on our local systems.
BAR has quietly become the best RTS to release in years and is a huge amount of fun. It really feels like the version of TA that my nostalgia remembers even though the game and units are a bit different.
My group don't play competitively, we hop on for a bot bash once a week and the AI is a lot of fun to play against. I'm excited for them to finally release on Steam because that will lower the barrier to entry and increase exposure because the game definitely deserves success.
The maanHimself repository appears to be 35 hours older than the aloshdenny one based on `created_at` from the GitHub API. maanHimself's `pushed_at` predates aloshdenny's `created_at` too.
That doesn't guarantee maanHimself is the original author, but it's looking likely.
There's an issue with GPT-5.6 Sol where it sometimes starts mixing thinking with output and stops working[1]. Once it starts doing that, the session is essentially cooked and you need to do a bit of gymnastics if you want to recover it.
This happens to me more commonly in large projects (>100k LOC) and in those projects it seems to happen every few sessions. I feel this specific benchmark would be impacted by this more than the smaller contrived benchmarks.
[1]: https://github.com/openai/codex/issues/37524
I can't help but imagine agents using caveman speak sometimes start behaving in a stereotypically caveman manner, even if it's subtle. Is there a chance the agent does less reasoning because of it?
For those trying to get it to work in OpenCode with a Qwen Cloud Token Plan, this is what worked for me. Note that I've just matched Qwen 3.7 Max for the limits as I don't know exactly what they are.
"provider": {
"alibaba-token-plan": {
"models": {
"qwen3.8-max-preview": {
"limit": {
"context": 1048576,
"output": 65536
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"name": "Qwen3.8 Max Preview"
}
}
}
}
For the vast majority of models I've worked with, 150k tokens of context seems like some magic spot. If you can stay under it then the session will stay on track and the agent won't start getting forgetful and weird.
Just like with real work, it's valuable to break down big tasks into small tasks that you can knock over in a single session. When a session does start getting too big, you just need to ask the agent to reply with a comprehensive handover report and paste it into a new session.
Nirav from Framework is similar, he speaks openly about compromises they make with their designs and why they make them.
When leaders are both technical and open about these sorts of things it makes me feel like I can trust that they are invested in supporting and improving their products.
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.
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.
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.
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.
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.
Prompting isn't programming. Prompting is managing.
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.
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.
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.
I wonder how many thousands of hours I have put into this wonderful collection. My kids play them too.
There's some jank relating to fractional scaling on Wayland unfortunately, but I keep one monitor without scaling so when I want to play I just launch the puzzles on that.
I absolutely loved my Pebble. It was so amazing in its own niche.
I generally find with Nix and NixOS that I'm able to just use a dev shell to create little custom environments at runtime as needed. Another option is `mkOutOfStoreSymlink` if you want some dynamic config for some GUI you are running.
Depends on what you are trying to achieve though.
They say you shouldn't host status pages on the same infrastructure that it is monitoring, but in a way that makes it much more accurate and responsive in outages!
Crazy to think he died 26 years ago.
Open the Terminal and type help to start a puzzle, not much to it but it was a bit of silly fun!
It seems really straightforward to suggest that the better way to solve this is with standard protocols and self-hosting, but I do realise that's quite hand wavy and often not very accessible.
SMTP is an example of this succeeding, as problematic as that protocol is.
Not being forced to use iOS, but if you are on iOS you are forced to use the app store.
ECS architectures are used in a number of young open source game engines, such as Bevy[1]. I haven't done game development for a long time, but hearing about an architecture that does away with the heavy and complex OOP you often see in games makes me want to dip my toes in again and check it out.
[1]: https://bevyengine.org/
I thought this was quite well written. "Be pragmatic, not dogmatic" is a very sensible rule of thumb.
It appears I succeeded incorrectly, and "I C U".