dk189

Agreed, and that's basically our premise. If a 5 person team can post-train an open model to do this, so can the people you don't want doing it, model-level refusals on open weights are a speed bump. Which is the argument for defenders having it too, not against.

Fair, should've been precise. What's free today is the scan: read-only. The Bank of Anthos integer overflow is a scan finding, clone it and you'll get the same. The active mode that actually sends the exploit and shows the response is gated for now, that's the part that's really 'pen test'. Juice Shop's a fair target for showing it, will try to get this done and post an update.

Did you follow the link? There is a brew install binary you can install and test. It's live.

The tool is live, you can test it.

You need both, scanning for your own code, pen testing to actually prove vulnerabilities, otherwise it can be very noisy and one of the things that most tools currently suffer from is they give you too many false positives. For the moment. The pen testing we gated it for now until we resolve the debate of safety.

I think the policy universally makes sense, who would want to give a tool like this to bad actors? But it does leave a big section of the market underserved. Particularly when Mythos was made accessible to very large orgs and then Fable was pulled on export grounds.

Everyone's training AI to refuse. We trained a model to break in.

Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities.

AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access.

Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals.

For this project we've trained a specific model on a decade of capture-the-flag contests. This won't be made available to anyone and everyone, but we do believe that responsible developers and midmarket companies also need access to these tools in order to identify key vulnerabilities in their systems; not just enterprises.

We have developed two modes that run over a CLI:

• Security scan: a read-only audit of your local codebase for vulnerabilities. It only reports what it can tie to a specific file and line, so you're not wading through vibes-based findings. With exploit verification on, each finding is confirmed, reducing false positives that most other tools suffer from.

• Pen test: an active adversarial mode that will try to break a live system in a sandboxed environment. It proves each vulnerability by running the exploit and showing the request it sent and the response your code gave back, not a confidence score. Currently gated.

To show what the scan does, we pointed it at Bank of Anthos and it found an integer overflow in the transfer path: amount is an int, and amount + fee can overflow negative, so the balance check passes and you move funds you don't have. Plus the usual auth and secrets issues. (Bank of Anthos is Google's open-source bank. It's a known app and some of it is intentionally weak, which is the point: you can clone it and re-run the scan yourself instead of trusting a screenshot)

How the harness works:

Along with the model we built the harness to support this. The harness runs on a multi-agent swarm: an orchestrator splits the job across subagents running in parallel, each owning a slice, then synthesising one report.

The CLI is a local binary (brew/curl). It reads your code locally, then sends context to our inference API over TLS tcpdump it and you'll see exactly what leaves and where. Install is free; and you can run a scan for free up to 2m tokens, then need to pay for tokens beyond this. For full disclosure this is a product from Cosine (YC W23).

We're still deciding how to gate the pen-test mode, input welcome e.g. domain verification is one method that proves control but not necessarily permission.

Large Language Models like ChatGPT have showcased exceptional capabilities in natural language conversations, leading to a revolution in customer service automation. Unlike rigid, complex traditional NLP chatbots, a simple wrapper application around the ChatGPT API can significantly outperform them. Consequently, the market has now flooded with ‘Custom ChatGPTs’ solutions offered by a wide range of solutions, from solopreneurs to large, experienced companies in conversational AI.

At Algomo, we believe that the potential extends even further. We see language models as the foundational 'intelligence' driving autonomous AI agents in customer service.

Autonomous AI agents?

Standard conversational language models work by taking text input and producing text output. You ask a question, and the language model responds with ‘static’ information from a knowledge base. You can think of them as a ‘conversational search engine.’

LLM-based agents, however, are a step ahead. They not only take text as input but can also interact with 'modules' such as memory, call other specialized LLMs, utilize functions (tools & APIs), and even integrate human judgement. Essentially, they can strategize and execute solutions to any presented problem. Application in Customer Service

Autonomous AI agents can literally redefine the interaction landscape between businesses and their customers. For instance, an agent can integrate into a company's CRM system, using its memory module to recall past interactions and personalize responses. It can employ specialized LLMs to handle technical queries or access APIs for real-time order tracking, or product information, ensuring customers receive accurate and timely information. Even more impressively, these agents can autonomously escalate complex issues or ask feedback from human agents, combining AI efficiency with human empathy.

What is the difference against competitors eg Intercom Fin?