pull down to refresh

85 sats \ 3 replies \ @SimpleStacker 3 May \ parent \ on: What are your most surprising personal uses of LLMs? AI AskSN

Yes.... I do argue sometimes but it definitely poisons the well, in terms of triggering sycophancy.

Lately, I've found Opus to be more sycophantic, and ChatGPT to be almost too obstinate (or too unwilling to explore heterodox opinions)

write
compose
16 sats \ 2 replies \ @optimism 4 May

Opus has been tuned for instruction following so I'd use that model to make it do things; it's been trained on Claude Code conversations. GPT is trained to solve "complex problems".

Give the models what they are trained for: Ask open research questions to GPT, maybe add some roleplay. For Claude straight out just order it to research something.

If you need validation, ask the question you think you have the answer to without revealing the answer.

reply
85 sats \ 1 reply \ @SimpleStacker 4 May

good thoughts

do you use any models outside of Claude and gpt?

reply
118 sats \ 0 replies \ @optimism 4 May

For chat? I think I only use chat once a month. Grok works fine too. If I really have a one-off that doesn't fit in the framework, I just use Arena and yolo me an answer.

For dev-adjacent work I use mainly Claude, and GPT and GLM as secondaries. I used to use Kimi before GLM-5 was released.

For operational/integrated LLM flows for work (these must be local - no spyware!!!) I use mostly Gemma and Jan for structured output work and Qwen for embeddings.

reply