rlhf

1 article
sort: new top best
clear filter
google229 microsoft182 facebook159 bug-bounty125 exploit123 apple121 rce88 xss79 writeup59 cve57 browser52 react44 open-source44 docker43 malware43 account-takeover42 aws39 ai-agents36 supply-chain35 node30 dos30 ctf28 oauth27 privilege-escalation26 postmessage23 cloud23 sqli22 cloudflare22 cache-poisoning21 wordpress20 ssrf20 lfi20 automation19 pentest19 tool19 reverse-engineering18 machine-learning18 info-disclosure17 phishing17 llm17 kubernetes16 rust15 code-generation15 cors15 race-condition15 idor15 csrf14 opinion14 infrastructure14 privacy14
0 5/10
Show HN: Generator SFT and DPO datasets for tool-calling LoRA fine-tuning
tool

DataForge is an open-source toolkit for generating deterministic synthetic datasets for LLM tool-calling fine-tuning, featuring 8,500+ lines of code with anti-template detection and quality gates. The accompanying NHA Epistemic Deliberations dataset provides 183 real multi-agent reasoning sessions from 3-7 different LLM providers with convergence measurement and adversarial challenges for training reasoning-focused models.

llm-fine-tuning synthetic-data-generation sft dpo lora tool-calling dataset open-source multi-agent-reasoning chain-of-thought rlhf preference-learning data-quality epistemic-reasoning
DataForge NotHumanAllowed Anthropic OpenAI Gemini DeepSeek Grok Qwen 7B PROMETHEUS CASSANDRA ATHENA Geth Consensus
nothumanallowed.com · senza1dio · 1 day ago · details · hn