Pi 1.0(earendil.com)
1618 points by sergiotapia | 553 comments
Earendil announces the 1.0 release of Pi, a hardened, minimal, extensible AI agent harness used by hundreds of thousands of people weekly.
First screen, captured .
Looks similar
You said no MCP(earendil.com)
641 points by yarapavan | 351 comments
Earendil Engineering post explaining why their Pi coding agent, previously opposed to MCP, now supports the Model Context Protocol.
Measuring the sloppiness of code(earendil.com)
238 points by doppp | 222 comments
Pi Durable(earendil.com)
474 points by paulsmith | 65 comments
Earendil announcement of Pi 1.0 alongside Pi Durable, an experimental package for long-running, durable, malleable AI agents that can run anywhere.
How Compaction Works in Pi(earendil.com)
193 points by tosh | 81 comments
Pi's Minimalism Is Its Advantage(earendil.com)
487 points by luispa | 257 comments
Earendil post arguing that Pi, a minimal AI coding harness, gains performance and cost advantages by avoiding the complexity of larger agent tools.
Related stories
API Shouldn't Redirect HTTP to HTTPS(jviide.iki.fi)
584 points by oherrala | 252 comments
Blog post arguing that APIs should fail visibly on plain HTTP requests instead of redirecting to HTTPS, noting many major API providers don't.
The Twitter API is now effectively unmaintained(snarfed.org)
363 points by edent | 461 comments
Ryan Barrett's blog post arguing the Twitter API is effectively unmaintained, citing the decline of Twitter employee posts on the developer forum.
The problem is not AI code, but not knowing about system architecture or intent(ssp.sh)
317 points by zazuke | 204 comments
A short note in a personal knowledge base arguing that the real problem with AI-generated code is that teams no longer understand their system architecture or the intent behind design decisions.
Open Source is one person(opensourcesecurity.io)
325 points by LawnGnome | 132 comments
Blog post by Josh Bressers on Open Source Security arguing that many open source projects are maintained by a single person.
GPT-4.1 in the API(openai.com)
659 points by maheshrijal | 484 comments
OpenAI announcement introducing the GPT-4.1 model series in the API, with improvements in coding, instruction following, long context, and a new nano model.
There isn't an easy exploit for this PHP vulnerability(eliastaylor.com)
566 points by zkldi | 437 comments
Blog post arguing a newly disclosed PHP vulnerability is hard to exploit and that thousands of LLM-generated GitHub PoC exploits don't work against vanilla PHP.