More

localhost · 2026-11-06T20:06:20

it is more than possible - this is exactly what casey handmer and his startup terraform industries is doing in a pilot plant in the desert: https://blog.terraformindustries.com/2026/10/21/terraform-20...

localhost · 2026-10-28T18:21:58

still cheap compared to those things. lab down the hall in grad school had an onyx [1] with the fancy polarized shutter 3d glasses for playing what we called "chem tv" or semi-empirical small molecule docking experiments - that was something like $250k or so in the early 90s.

[1] https://en.wikipedia.org/wiki/SGI_Onyx

localhost · 2026-08-29T18:03:46

This is Amdahl's law in action. [1]

Until we figure out a good way to leverage humans in all of this ("Attention is all you need" applies equally to humans as it does to models) productivity gains for the system will always be limited by Amdahl's law. Gwern has an excellent post on this. [2]

[1] https://en.wikipedia.org/wiki/Amdahl's_law [2] https://gwern.net/guardian-angel

localhost · 2026-04-15T15:31:43

why can't this be a cli tool? then you can get an agent to write a script that programmatically calls the cli tool in addition to the agent calling it directly.

jauntywundrkind · 2026-04-15T16:16:53

It could be a cli tool, and it should be a cli tool, for exactly this reason.

Let the LLM work in code mode. Don't make it have to be the execution engine too. It can do it but it's slow and giving it tools script what it wants will go far better.

I do think there's an interesting possibility where we turn MCP into something composable. Capnproto has promise pipelining where you can issue new instructions with results you don't have yet. If MCP could copy those tricks, & express promises... and those promises worked across MCP servers ("third party handoff", https://github.com/capnproto/go-capnp/issues/597)... you'd start to have something as compellingly composable as the shell.

localhost · 2026-03-26T13:44:23

there is an activation energy cost to so many activities - so those things just never got done. many times it is because the cost-benefit wasn't clear at the start (unknown unknowns) so it never got done. kudos to op for experimenting and showing us one way of making something like this happen.

localhost · 2026-03-13T22:23:50

then have ai write a deterministic transformation tool that turns it into the specific style and standard that is needed

localhost · 2026-03-09T19:24:20

i had gpt-5.4 write a 6502 font version of this font [1] in between working on other things. super fun and learned a lot by watching it do its thing.

[1] https://github.com/jflam/6502-sans

localhost · 2026-02-01T16:58:24

tbf neither does anthropic

localhost · 2026-01-15T00:59:35

This is what ACP and https://github.com/zed-industries/claude-code-acp enables. ACP controls agents - there is native support in Copilot CLI and Gemini and adapters for claude code and codex.

yencabulator · 2026-01-17T19:03:39

https://platform.claude.com/docs/en/agent-sdk/overview#get-s... reads to me like you have to use the public API for the Claude Agent SDK, not a Claude Code plan:

> Unless previously approved, we do not allow third party developers to offer Claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.

Imustaskforhelp · 2026-01-15T01:20:58

wow. ACP is used within zed so I guess zed is safe with ACP using claude code

I wonder if Opencode could use ACP protocol as well. ACP seems to be a good abstraction, I should probably learn more about it. Any TLDR's on how it works?

threecheese · 2026-01-15T02:13:50

According to Opus, ACP is designed specifically for IDE clients (with coding agent “servers”), and there’s some impedance mismatch here that would need to be resolved for one agent cli to operate as a client. I havent validated this though.

—-

1. ACP Servers Expect IDE-like Clients The ACP server interface in Claude Code is designed for: ∙ Receiving file context from an IDE ∙ Sending back edits, diagnostics, suggestions ∙ Managing a workspace-scoped session It’s not designed for another autonomous agent to connect and say “go solve this problem for me.”

2. No Delegation/Orchestration Semantics in ACP ACP (at least the current spec) handles: ∙ Code completions ∙ Chat interactions scoped to a workspace ∙ Tool invocations It doesn’t have primitives for: ∙ “Here’s a task, go figure it out autonomously” ∙ Spawning sub-agents ∙ Returning when a multi-step task completes

3. Session & Context Ownership Both tools assume they own the agentic loop. If OpenCode connects to Claude Code via ACP, who’s driving? You’d have two agents both trying to: ∙ Decide what tool to call next ∙ Maintain conversation state ∙ Handle user approval flows

ikidd · 2026-01-15T03:44:05

opencode acp -- start ACP (Agent Client Protocol) server

threecheese · 2026-01-15T02:14:22

[flagged]

Imustaskforhelp · 2026-01-15T02:29:45

WHAT??

Edit: I may have been rude previously but I was feeling beyond angry because I have tried to be a part of the community and I don't even know what to say

I genuinely am speechless. I think its so sad to see HN community be unable to trust and how you accuse me man which is so sad to see.

I genuinely just don't know what to say? I hope you are (jokng or something?) but what sort ofjoke is this?

localhost · 2026-01-11T15:17:22

Around 1980, while taking a "Saturday Morning Class" in Toronto - I discovered that there was a lab of ~24 Commodore PET 2001 (8K - blue phosphor, chiclet keyboards) at George Brown College. Spent as much time as I could there engaging with the early hacker community who all brought their shoeboxes of 5-1/4" floppies to trade programs. It was there that I had my first OMG moment when a much older kid showed me his floppy disk catalog program that could sort so much faster than mine did (he used quicksort).