Submissions from quesma.com

		RTK reports token savings, but our cost benchmarks disagree (quesma.com)
		170 points by michalwarda 20 days ago \| rank \| 84 comments
		Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses (quesma.com)
		285 points by stared 23 days ago \| rank \| 140 comments
		Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses (quesma.com)
		3 points by stared 27 days ago \| rank \| 1 comment
		Mushroom hunting with LLMs: what can go wrong? (quesma.com)
		54 points by stared 29 days ago \| rank \| 71 comments
		Benchmarking Qwen3.8 27B quantizations: 4-bit holds up, 1-bit collapses (quesma.com)
		15 points by stared 36 days ago \| rank \| 2 comments
		Claude Code pricing: same tokens, same model, up to 40x the price (quesma.com)
		31 points by jakozaur 51 days ago \| rank \| 10 comments
		Tokenflation: When "Hi" triggers 33 tool calls (quesma.com)
		6 points by jakozaur 67 days ago \| rank \| 1 comment
		I burned all my tokens researching how to save tokens (quesma.com)
		180 points by bkotrys 74 days ago \| rank \| 212 comments