leekrasnow
No user record in our sample, but leekrasnow has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
No user record in our sample, but leekrasnow has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.
em-dashes are a symptom of the problem; they are one of the “dead giveaways” mentioned in the OP which is why I brought them up as an example of slop-scrubbing before forwarding to other humans
Adapting the workflow to this new paradigm is a different sort of puzzle. I think that the folks whom enjoy agentic pair programming have found various satisfactory solutions. As a puzzle enthusiast myself, I have been…
I disagree with the premise of automatically dismissing sloppypasta just because it is verbatim LLM output. The sender could hypothetically have spent real effort in the chat interaction that led up to the ctrl-C…
this is sadly spot on
I am a craftsman of fine puzzles made from wood and CNC machined metal. I use LLM in lots of ways to help on individual parts of bigger puzzle design projects, like for example to create custom puzzle solver software…
fantastic insight, thanks for sharing these thoughts!
Thanks for sharing this. I am curious to know if your agent can connect to a user’s custom MCP server in order to make tool/calls with files attached. For example I have a custom MCP server that catalogs the images…