News for hackers. Stuff that matters.
Re:OpenLogi by breznev on Tuesday August 18, 2026 @11:34PM (#49356385)
Oh it’s not just the site—the app is obviously LLM generated too and feels like it. I gave up and went back to Mos within 20 minutes.
Re:OpenLogi by transitorykris on Tuesday August 18, 2026 @11:57PM (#49356551)
At this point we should be sharing prompts not code for solutions like OpenLogi. Reverse engineering many things can typically be one-shotted (ignoring things like.. capturing a pcap or whatever to aid the effort). Let others add their own taste to the solution.
Re:OpenLogi by _345 on Wednesday August 19, 2026 @12:38AM (#49356908)
Isn't it wasteful to have everyone go off and remake the same software with slightly different bugs in it instead of one that fixes almost all of the bugs
Re:OpenLogi by Barbing on Wednesday August 19, 2026 @01:59AM (#49357449)
Terribly wasteful, yes, though perhaps if the idea caught on the major labs could stand some chance of long-term profitability.
Re:OpenLogi by seaal on Wednesday August 19, 2026 @01:01AM (#49357059)
Seriously, I wonder how many tokens are generated (wasted) every day on someone recreating another agent memory, context management, code graph, etc.

I can’t wait until Qwen 4.5 27B or Gemma 5.

Re:OpenLogi by al_borland on Wednesday August 19, 2026 @02:13AM (#49357534)
It then becomes a roll of the dice if someone ends up with working software.
Re:OpenLogi by dgellow on Wednesday August 19, 2026 @03:59AM (#49358438)
Please no, I couldn’t care about your prompts, there is nothing special about them. Anyone can look at the generated artifact and reverse engineer their own prompt in no time
Re:OpenLogi by jklp on Thursday August 20, 2026 @07:17PM (#49381597)
You're forgetting the other half of using the software you created - you still need to maintain it!