Florian Gitt @gitthub

There may not be many people left in 10 years who can write, or want to read, things longer than a page or two. But there will be at least a few of us, and we'll be a powerful club.

Unbeatable!!

plannotator @plannotator

14 hours ago

Plannotator 0.27.6 is out. Webapp annotation for TUI users. Annotate: - webapp annotation via local proxy - HTML annotation optimizations - Ability to remove agenttui or configure it Code Review: - generated files (eg lock) collapsed by default Other various fixes and

8 5 98 4K 45

Coding agents are becoming runtimes! herdr.dev/blog/coding-ag…

Vercel Developers @vercel_dev

3 days ago

Introducing fx, a tiny, open, native coding agent from Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single

173 268 3K 922K 2K

I'm so incredibly tired of seeing low-effort AI-designed web pages. I basically bounce off any new product immediately when I see it (never get a chance to judge the product itself). Lots of thin lines, glowy styles, inconsistent fonts, lots of monospace. You know who you are.

For anyone with endless ideas, this agent age is nirvana as those ideas are met with endless execution, endless exploration. I've never had has much fun working with computers as I do right now. What a time to be alive.

my favorite way to explain people herdr is to just open a new workspace, launch an agent and tell it to: read `herdr --skill` then split 10 other panels that make my computer look like some scifi hacker terminal from the movies

big update: herdr is joining Y Combinator, F26 batch. herdr has been a solo project from day one. in four months it reached a place i couldn't have imagined; and that's entirely thanks to this community. all the love, all the support, all of you. i'm so grateful, thank you! this doesn't mean herdr is going closed. the whole idea from the start: herdr is the open agent runtime, you use it freely, you build on top of it, and it carries your agentic work every day. that doesn't change. i'll be building on the same open runtime as everyone else. read the full story here: herdr.dev/blog/herdr-is-…

Yes yes yes.

vas @vasuman

2 weeks ago

x.com/i/article/2085…

191 415 4K 1.6M 8K

To understand and empathize with how workers in many or most fields outside software experience advances in AI capabilities, I propose a little thought experiment. x.com/i/article/2082…

Keep work across multiple folders in one Codex project. Local projects can now include related code, docs, and reference files from multiple folders. Codex can read and write across them while one primary folder remains the Git root.

I have never seen positive results from a large consulting company like McKinsey or Accenture who build AI for you In the last 3 years I’ve worked with over 25 companies who did this, and every single time they get an over complicated solution nobody understands coupled with a mountain of slides filled with unnecessary jargon like “knowledge graph ontology” Every single time the solution is to tear it down and only add complexity incrementally when there is a measurable reason to do so. Big consulting has incentives that run the other way so you have an ever lasting dependency on them. I can’t see how deploying this model en masse is going to create value. I think it works for Palantir because that approach is markedly different. People seem to have cargo culted the term forward deployed engineer without fully internalizing it. See barry.ooo/posts/fde-cult…

GPT-5.6 Sol confirmed to be an extremely good model

Claude @claudeai

a month ago

Beginning July 20, Claude Fable 5 will be included in all Max and Team Premium plans, at 50% of limits. Pro and Team Standard users will continue to have access to Fable via usage credits, and will receive a one-time $100 credit. Demand for Fable has been challenging to

5K 6K 54K 28.9M 7K

daily reminder, codex self control: it can list all the tasks and sessions that are available it can rename every single title it can send a message to each task from another thread.

x.com/i/article/2076…

"When intelligence is plentiful, volition is valuable. The people who are going to make a difference are not the ones who seek relaxation and passively use AI to work less. They are the ones who will seek improvement and actively wrestle with AI to develop their own mental capabilities and accomplish more." theatlantic.com/ideas/2026/06/…

[1/n] Recent OpenAI research has demonstrated the ability of LLMs to solve frontier problems in mathematics. We design a simple pipeline (using GPT 5.5 Pro and Claude Opus 4.8) that resolves 9 challenging open problems, including open problems from prominent theoretical computer science venues—4 from COLT open problem list and 1 from FOCS —as well as 4 problems from the commutative algebra. Project link: github.com/Pengbinghui/pi…, joint work with @runzhou_tao, Steven Wang & @HantaoYu_Theory

Most of Europe has not yet absorbed what AI is about to do to us. The few who have are not saying it loudly enough. We wrote Europe 2031: a five-year scenario of the continent's slide into irrelevance, how AI is driving it, and what can still be done to change course.

it's not done if it's not implemented it's not done if the implementation is ugly it's not done if it's not documented it's not done if users can't discover it it's not done if you can't market it

I want some kind of LLM workflow tool. • Ability to manage a set of input files (Markdown or similar), plus other general-purpose context. • With real-time collaboration. (And maybe some concept of snapshots or VCS integration.) • And the ability to create/manage a inference workflows and a stored set of prompts. • Access to general-purpose coding agents (and not just chat models). • Some concept of compiled outputs/inference results (which ideally can be shared externally). Many projects have this feeling: "there is all this stuff, which I want to process/compute over in this iterated way, with some build artifacts being important/worth saving." GNU Autotools x Notion or something. Is anyone building this?