Content
@
0 reply
0 recast
2 reactions
downshift - μ/acc
@downshift.eth
my hot take on AI-assisted coding: it's now easier than ever to tangle yourself into a big ball of unmaintainable spaghetti if you don't know what you're doing but competent teams can also achieve very scalable + well-engineered systems much faster than ever before the human in the loop is still absolutely crucial
10 replies
3 recasts
30 reactions
Matthew Fox 🌐
@matthewfox
spot on but more and more I am getting convinced this is mainly a reasoning limitation that can be fixed with enough agents in the pipeline its the one shot that makes it so inconsistent, the extra context helps but breaks character limits and muddies the problem solving Half the time you can see yourself that the ai is wrong while its writing a solution but it has nonway to course correct at the minute
2 replies
1 recast
3 reactions
downshift - μ/acc
@downshift.eth
i think you are correct that we can improve a *lot* with current tech but, counterpoint: great system design can exist at the edge of even humans’ cognitive abilities and requires experience and creativity in bespoke situations that are beyond what’s available in a LLM’s training set (however huge) perhaps we need large models that are somehow trained on a higher dimension than serialized tokens, or on data that is otherwise modeled to better fit a specific domain like distributed systems? (cc @swabbie.eth) my head hurts 😅
1 reply
0 recast
2 reactions
sean
@swabbie.eth
i think groups of specialized agents (with different specialties) could solve these issues, but it will take 5+ years before coordination doesn't get tied up in knots a decent percentage of the time
0 reply
0 recast
1 reaction
