HNHacker News
TopNewBestAskShowJobs

doshay

37 karma · joined June 29, 2025

i’m convinced the way we build software is about to change. trying to help make that future real. i’m super curious about everything related to that

web: https://shaylivni.com

gh: https://github.com/shayliv

in: https://www.linkedin.com/in/shay-livni/

x: https://x.com/IvniShay

submissionscomments
doshay··on [dead]
proof you can do amazing things with only html (and some <script> tags :)
doshay··on Show HN: Deliberate – log what your agent rejected, not just what it ran
Nice direction !

Just curious, how can Deliberate exactly identify the options the agent faced? and what do you consider an "option"? sometimes it can be vauge (say the agent decided to explore this way and not that way, would that be considered an option?)

anyway, i like seeing tools like that! good luck

doshay··on Show HN: An open-source, interactive AI engineering syllabus (1,100 papers)
seems like the link is not attached :X
doshay··on Show HN: I Built a Debugging Challenge for the AI Coding Age
it means using coding agents (cc) is allowed? anyway, nice idea. will give it a try
doshay··on Show HN: Git for AI Agents
cool approach, i havent used jj actually in my workflow, ill try to adopt
doshay··on Show HN: Git for AI Agents
sure, fair question i think the main difference is that entire are built on top of git == you would have to commit in order to track something...
doshay··on Show HN: Git for AI Agents
i think you misunderstood the concept, actually . it's not built to replace git, rather to sit on top of it.
doshay··on Show HN: Git for AI Agents
https://github.com/regent-vcs/re_gent
doshay··on Show HN: Git for AI Agents
that's exactly what i tried in the first place, but i think it would be misuse of git protocol, git is built for files - the blobs/ tree calc & mechanism , for large contexts and linear thinking flow it's differnt, but honestly - i think you can get to a very good solution with pure git..
doshay··on Show HN: Git for AI Agents
at the moment only Claude Code, i'm planning to add support for the other big 3, but at the moment it's just me ... hopefully in the near future :)
doshay··on Show HN: Git for AI Agents
thanks! will do
doshay··on Show HN: Git for AI Agents
cool!

actually not at the moment - would be nice to add it. i think the core of re_gent allows it very naturally, feel free to push it if want :)

doshay··on Show HN: Git for AI Agents
exactly, imo - the llm should touch git only after explicit approval or after specific set of guardrails. this one of the reasons i built it actually, i think the agent workflow should be decoupled from git, until saving the code
doshay··on Show HN: Git for AI Agents
super nice, indeed similar approach
doshay··on Show HN: Git for AI Agents
but then you would have to commit each tool and action of the agents, which is polluting the git history and also huge overhead (at least imo)
doshay··on Show HN: Git for AI Agents
absolutely right, i got this feedback from many people actually ...
doshay··on Show HN: Git for AI Agents
- hopefully after a /compact. - what happens if want to undo, and then redo? i found the /rewind functionality in claude very lean in that matter.
doshay··on Show HN: Git for AI Agents
tnx for the honest feedback! really, appreciate it! would you mine sharing more details about your workflow with jj?