Y
Hacker News
new
|
ask
|
show
|
jobs
user:
GabrielBianconi
created:
2013-08-09
karma:
181
co-founder @ tensorzero – open-source LLM infra
https://github.com/tensorzero/tensorzero
submissions:
0 points
|
0 comments
Even (very) noisy LLM evaluators are useful for improving AI agents
35 points
|
10 comments
Designing for Agents
1 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
We're building an automated AI engineer, and it works
3 points
|
0 comments
Mitchell Hashimoto on Feature Design [video]
3 points
|
0 comments
Bandits in Your LLM Gateway
3 points
|
0 comments
Claude Plays Catan [video]
3 points
|
0 comments
Is OpenAI's Reinforcement Fine-Tuning (RFT) Worth It?
4 points
|
0 comments
How Kimi K2 achieves efficient RL parameter updates
3 points
|
0 comments
Ask HN: How much would it cost to own and operate a personal gTLD?
3 points
|
1 comments
Deploying DeepSeek on 96 H100 GPUs
285 points
|
80 comments
Sporks of AGI: why the Real Thing is better than the Next Best Thing
3 points
|
0 comments
We raised $7.3M to build an open-source stack for industrial-grade LLM apps
1 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Ask HN: How does the Postgres ecosystem compare to Vitess at 1PB+?
4 points
|
2 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Fine-tuned small LLMs can beat large ones with programmatic data curation
53 points
|
11 comments
0 points
|
0 comments
0 points
|
0 comments
Supervised fine tuning on curated data is reinforcement learning
71 points
|
19 comments
0 points
|
0 comments
<syntax-highlight>: custom element that uses the CSS Custom Highlight API
2 points
|
0 comments
0 points
|
0 comments