651–660 of 700 posts
Earlier quoted context omitted.
> would likely increase costs overall Assuming you pay per token, which seems like a really strange workflow to lock yourself into at this point. Neither paid monthly plans nor local models suffer from that issue. I tried once to use APIs for agents but seeing a counter of money go up and eventually landing at like $20 for one change, made it really hard to justify. I'd rather pay $200/month before I'd be OK with tha…
The $20-per-change problem is a workflow problem, not a pricing problem. Batching work into larger well-scoped sessions rather than interactive back-and-forth changes the unit economics significantly. Most people use these tools like a terminal — one command at a time — which is the worst possible cost profile.
The only thing I'm wondering is if they have eval frameworks (for lack of a better word). Their prompts don't seem to have changed for a while and I find greater success after testing and writing my own system prompts + modification to the harness to have the smallest most concise system prompt + dynamic prompt snippets per project. I feel that if you want to build a coding agent / harness the first thing you should…
Have to watch out for other plugins trying to do the same, though.
[flagged]
This is another one of OpenCode’s current weak points in the security complex: They consider permissions a “UX feature” rather than actual guardrails. The reasoning is that you’re giving the agent access to the shell, so it’ll be able to sidestep everything. This is of course a cop-out: They’re not considering the case in which you’re not blindly doing that. Fun fact: In the default setup, the agent can fully edit al…
[flagged]
Granted, I just started playing around with OpenCode (but been using Codex and Claude Code since they were initially available, so not first time with agents), but anyways: > they need broad file system access to be useful, but that access surface is also the attack surface Do they? You give them access to one directory typically (my way is to create a temporary docker container that literally only has that directory…
[flagged]
I created a tool for this: https://github.com/Use-Tusk/fence Same thoughts - I wanted a "permission manager" that defines a set of policies agnostic to coding agents. It also comes with "monitor mode" that shows operations blocked, but not quite an audit log yet though.
Earlier quoted context omitted.
Anthropic needs to spend some tokens rewriting Claude Code in Rust (yes, really). The difference in feel between Codex and Claude Code is obvious. The whole thing is vibed anyway, I'm sure they could get it done in a week or two for their quality standards.
Java (incl. Scala, Closure, Groovy, Jython, etc.) is better suited to running as a server. Let agents write clean readable code and leave performance concerns to the JIT compiler. If you really want you can let agents rewrite components at runtime without losing context. Erlang would offer similar benefits, because what we're doing with these things is more message passing than processing. Rust is what I'd want agent…
Also, it'll be hard for them to lure good people to work on that thing. Absolutely no one is getting excited to write, vibe, or maintain Java.
Earlier quoted context omitted.
Java (incl. Scala, Closure, Groovy, Jython, etc.) is better suited to running as a server. Let agents write clean readable code and leave performance concerns to the JIT compiler. If you really want you can let agents rewrite components at runtime without losing context. Erlang would offer similar benefits, because what we're doing with these things is more message passing than processing. Rust is what I'd want agent…
There is literally no reason to write it in a JVM language in 2026 when better options exists. Either Go for simplicity and maintaininability or Rust to get the most out of the machine works. Also, it'll be hard for them to lure good people to work on that thing. Absolutely no one is getting excited to write, vibe, or maintain Java.
Earlier quoted context omitted.
For a TUI agent, runtime performance is not the bottleneck, not by far. Hackability is the USP. Pi has extensions hotreloading which comes almost for free with jiti. The fact that the source is the shipped artifact (unlike Go/Rust) also helps the agent seeing its own code and the ability to write and load its own extensions based on that. A fact that OpenClaw’s success is in part based on IMO. I can’t find the tweet…
OK, make sense, but there are also claw clones that are in Rust (and self modifying). Also python ones would also allow self modifying. I'm always puzzled (and worried) when JS is used outside of browsers. I'm biased as I find JS/TS rather ugly language compared to anything other basically (PHP is close second). Python is clean, C has performance, Rust is clean and has performance, Java has the biggest library and ca…