In their case, context management pays off more the tighter your window. Their gap between managing and not managing is 35.7 points of success rate at 32k and 2.7 points at 128k. My version of that was a rule I stick to, as much as I can. I checkpoint a session at about 25-30% of the window, write the state out to a PROGRESS.md and a JSON file of the requirements, and start fresh. This restart costs me 30 seconds, since a bloated session doesn't get any cheaper the longer you stay in it.
Also worth knowing that the models are Nemotron-3 and Mistral-Medium, not the frontier models most people here are paying for.
And what you describe doing is also very in line with Cursor's published recommendations.
Though of course every single element of their application's actual UX is pushing hard in the opposite direction. The cynical part of me can't help but notice that there's a bit of a conundrum here: using coding agents more effectively seems to involve working pretty hard at giving the agent vendor less money.
This could potentially be an important part of price discovery, though. The market is constantly seeking that balance point between 'chasing whales' and 'making it up on volume'.
rahulmax · · focus · HN ↗
<a href="https://rahulmax.com/notes/how-i-keep-the-ai-bill-down/" rel="nofollow">https://rahulmax.com/notes/how-i-keep-the-ai-bill-down/
In their case, context management pays off more the tighter your window. Their gap between managing and not managing is 35.7 points of success rate at 32k and 2.7 points at 128k. My version of that was a rule I stick to, as much as I can. I checkpoint a session at about 25-30% of the window, write the state out to a PROGRESS.md and a JSON file of the requirements, and start fresh. This restart costs me 30 seconds, since a bloated session doesn't get any cheaper the longer you stay in it.
Also worth knowing that the models are Nemotron-3 and Mistral-Medium, not the frontier models most people here are paying for.
bunderbunder · · focus · HN ↗
Though of course every single element of their application's actual UX is pushing hard in the opposite direction. The cynical part of me can't help but notice that there's a bit of a conundrum here: using coding agents more effectively seems to involve working pretty hard at giving the agent vendor less money.
slfnflctd · · focus · HN ↗