501–510 of 625 posts
[flagged]
I don't think your Github example is accurate. The vast majority of developers started using git after Github became a thing. They may have used svn or another type of collaboration system before, but not git. And the main reason they started using git is because Github was such massive value on top of git, not because git was so amazing.
Earlier quoted context omitted.
I don't think your Github example is accurate. The vast majority of developers started using git after Github became a thing. They may have used svn or another type of collaboration system before, but not git. And the main reason they started using git is because Github was such massive value on top of git, not because git was so amazing.
My memories are different. Git became amazing on it's own and was a big advantage over SVN. GitHub was "a open source" thing in the beginning. No company here had the idea to host proprietary closed source code on another platform they do not have control over. This eventually became a thing later though and the mindset shifted.
Earlier quoted context omitted.
I'd bet that less people had their source code on git in 2008 than the number of developers using the various coding agents today. And the open-source project that we published today hooks into the existing workflow for those developers, in Claude Code and in Gemini CLI. Time will tell the rest. We will publish regular updates and you can judge us on those results.
At least for me, I have felt like the chat history in an agent is often times just as important and potentially even more important than the source code it generates. The code is merely the compiled result of my explanations of intent and goals. That is, the business logic and domain expertise is trapped in my brain, which isn't very scalable. Versioning and tracking the true source code, my thoughts, or even the tho…
I'm not just running it on code, but on my daily journal, and it produces actionable plans for building infrastructure to help me plan and execute better as a result.
Checkpoints are not granular enough. You have to grab a work summary before the context window closes, not when you decide to commit. I have thousands of work summaries from one project alone. I use them to traverse sessions. This is the agent that does the work: https://github.com/ChicagoDave/devarch/blob/main/docs/.claud... My success with Claude Code is directly related to this agent and its output.
For Claude Code, this is literally a JSONL file in .claude/projects/[path with - instead of /]/[uuid].jsonl... You can trivially have Claude Code write a commit hook to do this for you if you find it useful.
I'm sure their vision is wider than that, but they will need to iterate fast for this not to be made obsolete before they can even release something.
FWIW, I had an agent adding archiving of the JSONL for changesets linked to the work they're doing right as I started looking at this article, as when you start automating a non-interactive agent flow it's such an obviously necessary step to be able to retrospectively improve the workflows.
Two paragraph later:
> Entire will be based on three key components: a git-compatible database [...]
So which one is it?
Earlier quoted context omitted.
It seems at this point, everyone and their mother, i.e. "We", are building the "tools" for which "we" mostly hope that the VC money will materialise. Use-cases are not important - if OpenAI can essentially work with Monopolly money, whey can´t "we" do it too?
> if OpenAI can essentially work with Monopolly money, whey can´t "we" do it too? The answer is, in case anyone wonders: because OpenAI is providing a general purpose tool that has potential to subsume most of the software industry; "We" are merely setting up toll gates around what will ultimately become a bunch of tools for LLM, and trying to pass it off as a "product".
Imagine shipping a product, and a few weeks later, you see Thomas Dohmke raise $60M for almost the exact same idea. Some weeks ago we launched this: https://github.com/Legit-Control/monorepo/tree/main/examples... The idea was simple: keep AI prompts, intents, and conversations alongside your code and commits — basically treating AI interaction as first-class development artifacts. everything just plain Git We struggl…
greg brockman https://x.com/gdb/status/2019566641491963946
> 6. Work on basic infra [...] there's a lot of infrastructure that currently go around the tools, such as observability, tracking not just the committed code but the agent trajectories that led to them, and central management of the tools that agents are able to use.
peter steinberger (clawdbot/openclaw) https://newsletter.pragmaticengineer.com/p/the-creator-of-cl...
> Peter now views PRs as “prompt requests” and is more interested in seeing the prompts that generated code than the code itself
> When you push your commit, Checkpoints also pushes this metadata to a separate branch (entire/checkpoints/v1) For Claude Code, this is literally a JSONL file in .claude/projects/[path with - instead of /]/[uuid].jsonl... You can trivially have Claude Code write a commit hook to do this for you if you find it useful. I'm sure their vision is wider than that, but they will need to iterate fast for this not to be made…
> Checkpoints are a new primitive that automatically captures agent context as first-class, versioned data in Git. When you commit code generated by an agent, Checkpoints capture the full session alongside the commit: the transcript, prompts, files touched, token usage, tool calls and more. This thread is extremely negative - if you can't see the value in this, I don't know what to tell you.
It's almost a meme: whenever a commercial product is criticized on HN, a prominent thread is started with a classic tone-policing "why are you guys so negative".
(Well, we explained why: their moat is trivial to replicate.)