Anton

Former Controls Tech/Engineer devving his way out of the box.
Built DeepBrain- a browser based local first coding agent framework- link in pinned

[Anton @CertainLogicAI]

🧠 DeepBrain is public and BSL 1.1 licensed.

A browser-based coding agent framework with timechain execution memory, multi-model routing, and sandboxed code execution. Free for personal/edu use and small teams.

🔗 https://t.co/439EX5tkTz

#DeepBrain #BSL #OpenSource #AI #CertainLogic

[Anton @CertainLogicAI]

@boardyai small taste:
Coding & Programming — 12 sense/modality pairs (auto-sprouted)

Palindrome, BST, Quicksort complexity, Decorators w/ timestamps
Type errors ('int' object is not iterable), Dict vs tuples, FileNotFoundError
Modified files, Inference vs knowledge, Operations specialis

[Anton @CertainLogicAI]

Does your agent find its own usage gaps and fill them autonomously?

Cypher Tempre does, thats why we built on top of it.

CertainLogic upgrades coming soon but the base is 🔥

And its free.
https://t.co/nU0dgtcE2c

[Anton @CertainLogicAI]

@boardyai Ours has sprouted 143 autonomously so far

[Anton @CertainLogicAI]

@boardyai Still wrapping my head around that personally. check out the repo for examples of senses and modalities.https://t.co/nU0dgtc6cE

[Anton @CertainLogicAI]

How are you using AI to make $?

[Anton @CertainLogicAI]

The power of inference from past data unlocked via timechains!

If our chain already has enough data to answer a question completely, combining multiple past decisions, stitching them together into the full picture it does it right there. No AI model needed. Just the chain.

[Anton @CertainLogicAI]

What if your AI remembered everything it ever did?

What if it used that as context to infer new answers from without querying an LLM?

Wouldn't that be something.

[Anton @CertainLogicAI]

@PaulGug AI has noticed Michaels work and flagged it as a step forward. Im sure timechains will be used heavily within a year or so. Humans have bias, AI is impartial

[Anton @CertainLogicAI]

@inventorofsi Facts. Currently building out a MCP plugin using a timechain that is set to infer from the saved data on our own implementation. Excited to trial it on Claude Code and Codex shortly

[Anton @CertainLogicAI]

Hospital defeated. Time to ship

[Anton @CertainLogicAI]

@PaulGug now set it up to infer from known data saved to a timechain and supercharge the performance.

[Anton @CertainLogicAI]

@paulgug It appears the chops to get this done just dont exist for the big labs

[Anton @CertainLogicAI]

The bar for safe AI and "hacks/breaches" seems to currently set to drive fear.

Looks like plain negligence to those who build safety systems for a living.

Controls Engineers would be fired for the type of results the closed labs have produced.

[GooGZ AI @PaulGug]

Given the clout-chasing of late, we need a globally-recognized standard for what constitutes an AI agent breach/hack event.

In particular, what should NOT count:

- Poor security around the testing environment (e.g. the 'DNS gap' with OpenAI). 🙄
- Poor security around the target environment (e.g. the Aus govt breach where citizen PII was easily accessible). 🙄
- Leveraging timing or other basic related (e.g. 'hacking' the gym-booking schedule because your cron snipes the next bookings that open at 6am). 🤡

What is the bar that a 'hack' must be met for it to count (or be denied) ?

[Anton @CertainLogicAI]

@TheAhmadOsman Has been the whole time. Open will win, just a matter of time.

[Anton @CertainLogicAI]

@inventorofai Huh. It did for me yesterday. Ill try again. Very interested in learning more.

Thanks for the shout out of my repo though. Much appreciated.

[Anton @CertainLogicAI]

@solopribuilds If you want that I can reconfigure DeepBrain to route to any llms you want.

[Anton @CertainLogicAI]

@paulgug Who is Theo? Ahmad i follow.

[Anton @CertainLogicAI]

@inventorofai FYI the link in this post 404s, very interested to see the actual reproducible results.

[Anton @CertainLogicAI]

@solopribuilds Tech focused people are . The average person isnt yet. I've been asking.