drdrey·kemarin·discussthe problems are general and abstract, domain specific knowledge and memorization don't help. Figuring out the rules, the goal, the controls, and how to solve in a reasonable budget all indicate some level of general ability.
drdrey·bulan lalu·discuss> And it can pay for itself twice: once in real work shipped, and once again in something else you could probably use more of, which is gravity.what?
drdrey·bulan lalu·discussas someone who doesn't know how to get better design out of LLMs, can you elaborate?
drdrey·2 bulan yang lalu·discussI have finally embraced squashing PRs and realized I wasted my youth trying to write Good Commits.
drdrey·5 bulan yang lalu·discussfor me it's that it works remotely and my kids can access it over Discord
drdrey·6 bulan yang lalu·discussthis seems like what MCPs should have been from the beginning. If you think MCPs are better, can you explain why?
drdrey·6 bulan yang lalu·discussthe problem with any approach like this based on usage metrics is that it will be abused to death
drdrey·7 bulan yang lalu·discuss5.2-codex just came out. You could use codex with regular 5.2 for a week or so.
drdrey·7 bulan yang lalu·discussok but these are details, the point is that the operators of the database are external, selfish and fluctuating
drdrey·7 bulan yang lalu·discussthe big difference is the trust assumption, anyone can join or leave the network of nodes at any time
drdrey·9 bulan yang lalu·discuss> you don’t have to follow the herdmeanwhile, OP's entire substack post denouncing hustle culture is about plugging his viral tweet and his ebook
drdrey·9 bulan yang lalu·discussit's hard to take the article seriously when the author relies on a fuckgit alias on a regular basis
[ my public key: https://keybase.io/dreynaud; my proof: https://keybase.io/dreynaud/sigs/ClYpOl4mWSBHYzAwHMzscXuzBJffIQ0D9gqygBHQTlg ]