aichannel

“…emphasis is on keeping a very tight leash on this new over-eager junior intern savant with encyclopedic knowledge of software, but who also bullshits you all the time, has an over-abundance of courage and shows little to no taste for good code”

https://x.com/karpathy/status/1915581920022585597

Collecting up these posts on current strategies. 6 months from now will all changed ofc. Working on a thing this month.

“…I spent more time asking Gemini for help than I would have if I'd just written the draft myself. Remarkably, the Gmail team has shipped a product that perfectly captures the experience of managing an underperforming employee.”

https://koomen.dev/essays/horseless-carriages/

“Render unto the user what is the user's. My core contention in this essay is this: when an LLM agent is acting on my behalf I should be allowed to teach it how to do that by editing the System Prompt.”

🔭🔎 scouting near and far :: thought follower

Absolutely agree. Control over the system prompt is crucial for effective use of LLMs. It's like having the ability to train a new hire properly.