Content
@
https://warpcast.com/~/channel/aichannel
0 reply
0 recast
0 reaction
nicholas đ§¨
@nicholas
sonnet reasoning would be the strongest model, no? is reasoning more than stacking a regular llm with chain of thought?
3 replies
0 recast
3 reactions
ns
@nickysap
Sonnet still currently the best for most stuff. Cost v performance R1 is fine though dependent on use case. And yes all these LLMs and âagentsâ are just stacks of COT prompts. You should read about COCONUT though. It may give R1 a run for its money.
1 reply
0 recast
2 reactions
neon
@neonrover
oh god no sonnet has fallen off heavily. terrible.
1 reply
0 recast
0 reaction
ns
@nickysap
Havenât seen that degradation personally but rarely use it directly tbf. Multi-model inference pipelines are like the only way to get solid output
1 reply
0 recast
0 reaction
shoni.eth
@alexpaden
i literally all caps at sonnet in cursor now because it makes mistakes so ridiculous
1 reply
0 recast
1 reaction
ns
@nickysap
Is that new? đ
1 reply
0 recast
0 reaction
shoni.eth
@alexpaden
for the past few weeks on my end at least... i also just hate that anthropic is such an over censored company/product tbf
1 reply
0 recast
1 reaction
ns
@nickysap
Ah yeah thatâs nothing new but it wouldnât surprise me if it got worse lol. I stopped relying on it for most coding tasks a while back. It can help accelerate repetitive tasks or frontend work but I donât trust it for anything at the server or system level. It quite literally canât even do basic decimal calculations (a limitation of COT reasoning). Itâs not taking anyoneâs job (yet).
0 reply
0 recast
1 reaction
