GabrielBianconi's submissions

1.		Mitchell Hashimoto on Feature Design [video] (twitter.com/mitchellh)
		3 points by GabrielBianconi 4 days ago \| past \| discuss
2.		Bandits in Your LLM Gateway (tensorzero.com)
		3 points by GabrielBianconi 42 days ago \| past
3.		Claude Plays Catan [video] (youtube.com)
		3 points by GabrielBianconi 84 days ago \| past
4.		Is OpenAI's Reinforcement Fine-Tuning (RFT) Worth It? (tensorzero.com)
		4 points by GabrielBianconi 88 days ago \| past
5.		How Kimi K2 achieves efficient RL parameter updates (moonshotai.github.io)
		3 points by GabrielBianconi 3 months ago \| past
6.		Ask HN: How much would it cost to own and operate a personal gTLD?
		3 points by GabrielBianconi 3 months ago \| past \| 1 comment
7.		Deploying DeepSeek on 96 H100 GPUs (lmsys.org)
		285 points by GabrielBianconi 3 months ago \| past \| 80 comments
8.		Sporks of AGI: why the Real Thing is better than the Next Best Thing (sergeylevine.substack.com)
		3 points by GabrielBianconi 3 months ago \| past
9.		We raised $7.3M to build an open-source stack for industrial-grade LLM apps (tensorzero.com)
		1 point by GabrielBianconi 4 months ago \| past
10.		Ask HN: How does the Postgres ecosystem compare to Vitess at 1PB+?
		4 points by GabrielBianconi 4 months ago \| past \| 2 comments
11.		Fine-tuned small LLMs can beat large ones with programmatic data curation (tensorzero.com)
		53 points by GabrielBianconi 4 months ago \| past \| 11 comments
12.		Supervised fine tuning on curated data is reinforcement learning (arxiv.org)
		71 points by GabrielBianconi 4 months ago \| past \| 19 comments
13.		<syntax-highlight>: custom element that uses the CSS Custom Highlight API (andreruffert.github.io)
		2 points by GabrielBianconi 5 months ago \| past
14.		From NER to Agents: Does Automated Prompt Engineering Scale to Complex Tasks? (tensorzero.com)
		1 point by GabrielBianconi 8 months ago \| past
15.		Can reinforcement learning for LLMs scale beyond math and coding tasks? Probably (arxiv.org)
		6 points by GabrielBianconi 8 months ago \| past \| 4 comments
16.		Case Study: Automating Code Changelogs at a Large Bank with LLMs (tensorzero.com)
		1 point by GabrielBianconi 8 months ago \| past
17.		Show HN: TensorZero – open-source data and learning flywheel for LLMs (github.com/tensorzero)
		49 points by GabrielBianconi on Sept 16, 2024 \| past \| 2 comments
18.		Fast R-CNN – Overview (gabrielbianconi.com)
		1 point by GabrielBianconi on Feb 26, 2019 \| past
19.		R-CNN – Overview (gabrielbianconi.com)
		1 point by GabrielBianconi on Feb 14, 2019 \| past