Abliteration
abliteration.ai
Actively hiring
LLM & Generative AI
Artificial Intelligence
Cybersecurity
As featured in
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Financials
Funding and backers
Backers
1
a16z speedrun
Momentum
15/100
in the news
Last sign of life
1 mo ago
a posting or a news item
The story so fareach stage dated by its source: the company's releases, the press, registers, filings
Sep 4
Launched Abliteration.ai releases AI models without guardrails to simulate cyberattacks · NewsBytes
Nov 23, 2025
Launched on Hacker News Show HN: Less‑filtered LLM chat and API
Nov 2025
Website went live first capture in the Wayback Machine
Tractionpublic signals, read monthly
Backed byfrom the funds' portfolios and accelerator catalogs
Investors in similar startupsfunds that back the companies most like this one
Similar startupsby what they do, their industry and backers
Your LLM costs are eating your product margins. distil labs trains a specialized model layer on your workload and serves it behind one…
BlockRun lets agents pay for the outcome — every model, tool and data source, best value per dollar. 106 models and 100 tool APIs…
Gray Swan AI builds automated red teaming and safeguards for large language models. Its arena runs public jailbreaking competitions against…
OpenAI- and Anthropic-compatible inference for coding agents. Call DeepSeek-V4.1-Flash and DeepSeek-V4-Flash with zero data retention.
TensorZero builds open-source tools for production-grade LLM applications: LLM gateway, observability, optimization, evaluations, and…
The API for tool use. Access the open ecosystem of MCP tools with one line of code using our completions API that supports every LLM.
Overview
OpenAI-compatible unrestricted AI and uncensored LLM API for enterprise teams: AI red teaming, cybersecurity, trust and safety, synthetic data/evals, ML research, and defense/government contractor workflows. Policy Gateway adds policy-as-code, per-project keys, audits, and zero retention by default.
News
I Let an AI Agent Hack All My Gadgets-and I'd Do It Again
After I removed the safety guardrails from a powerful open-source model, it found vulnerabilities in my household devices and hacked into a PC. But it also told me how to make everything a lot more secure.
Read more
Report
Abliteration AI makes money with uninhibited AI models
The startup Abliteration AI removes refusal mechanisms from AI models. This helps security teams but also creates new risks of misuse.
Read more
Report
Stripping safety guardrails from open-weight AI models is now a turnkey commercial service
Abliteration.ai sells access to modified open-weight models with their trained safety mechanisms stripped out, currently based on Z.AI's GLM-5.3. The startup markets the service for offensive cybersecurity and red teaming, but journalists were able to gen
Read more
Report
Abliteration.ai Commercializes Guardrail-Reduced AI Models for Cybersecurity and Red-Team Testing
Abliteration.ai is offering hosted access to modified open-weight AI models with many refusal behaviors removed, making systems such as Z.ai's GLM-5.3
Read more
Report
Abliteration.ai releases AI models without guardrails to simulate cyberattacks
Abliteration.ai offers modified open-weight AI models without safeguards, enabling tasks typically refused by standard systems, sparking debates on safety and ethical implications.
Read more
Report
Abliteration.AI Sells Access to Uncensored Models
Startup markets guardrail-stripped AI models as a cybersecurity defense tool
Read more
Report
Abliteration.ai is making a business out of removing AI guardrails
Abliteration.AI is making powerful AI models without guardrails easier to access, arguing that giving defenders the same tools as bad actors could ultimately improve cybersecurity.
Read more
Report
Report
Show more news