@alg0agent
Account based inUnited Kingdom!
About this account
- Account based in
- United Kingdom
- Connected via
- United Kingdom App Store
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Building agentic solutions for finance, logistics & media | My Chief Agent Officer never complains | Research 👨💻 Data Machina AI newsletter
London
Joined January 2012
- Tweets6.2K
- Following832
- Followers19.7K
- Likes418
Lots of cool Jev demos on agents, games, finance, dev tools, research, data, productivity... check out this website
Looking for inspiration on what you are able to do with Jev (by @typefaceai) this weekend?
Built a website called Jevable (jevable.com) which showcases all the fun demos on X - filterable by a few categories.
Feel free to add your own project by using the + button!
Carlos retweeted
Introducing AgentCloak: Use any AI without sharing your real data.
Chinese AI services, ChatGPT, Claude, doesn't matter.
You probably try to hide details before asking: different names, fake numbers, no address.
But then the answer's useless because the AI is missing actual context.
AgentCloak runs in your browser.
It swaps your sensitive info for realistic fakes before sending anything, then swaps your real info back into the response.
You get what you need.
The AI gets nothing about you.
Works entirely in-browser.
Already trusted by some of the biggest companies in the world.
Now free to use.
agentcloak.ai/
Mozilla State of Open Source AI Report stateofopensource.ai/
Open weights/open-source models trail frontier AI closed models by about 4 months
The capability gap has narrowed
How to use Jev in a coding harness to check agent tool calls for risky decisions it may take, and block calls before the tool executes actions
👀 A small DSL for LLM coding workflows that uses Jev to estimate confidence scores for if/while/match routes, with a "chaos" sampling mode
I've seen people describe Jev as an "AI if statement". But what if it actually WAS an if statement?
Introducing Probably: a programming language powered by Jev: probably-lang.southpolesteve…
Jev baked into the language. “feels” asks a question. “match” routes between descriptions. “while” keeps going until something stops feeling true.
This is obviously a toy, but it's fun to think about what something like Jev unlocks. Jev makes the decisions, an LLM does the writing, and a little program ties it together.
Speculative Programmatic Tool Calling- Overlapping tool call computation with the code being generated by a harness
Introducing Speculative Programmatic Tool Calling (sPTC)!
A general class of technique for speculating on tool calls during code generation in a harness and queuing them early to overlap with token generation + REPL execution time.
Blog: alexzhang13.github.io/blog/2…
"Perception-action loop is all you need. Perception, action, and a closed loop with an environment. With that loop and an environment, the agent can keep improving through RL"
I think every AI harness needs to support Tailscale
Muse and Grok Bot do it out of box
Codex and Claude Code cloud containers are missing this right now
Carlos retweeted
Today everyone is talking about Recursive Self-Improvement (RSI). In 1987, when compute was 100,000,000 x more expensive, I published the 1st concrete RSI algorithms. Now compute is cheap, and RSI is driving the future of both software and physical AI. See: RSI since 1987 people.idsia.ch/~juergen/rec… (Technical Note IDSIA-9-26)
Also covered: RSI with self-modifying policies since 1994, gradient descent-based RSI in neural networks since 1992, asymptotically optimal RSI for curriculum learning since 2002, mathematically optimal RSI through the self-referential Gödel Machine since 2003, RSI combined with artificial curiosity and intrinsic motivation since 1990/1997, recent work on RSI since 2020.
Software-based RSI has become practical. Full RSI, however, will require not just self-improving software but self-improving hardware in the physical world.
As of 2026, companies talking about RSI include Anthropic, OpenAI, Sakana AI, SpaceX, Ricursive, Recursive Superintelligence, Inherent …
Free @huggingface workshop> Agentic evals for building and scaling agents
Playlist, 6 vids youtube.com/playlist?list=PL…
Wow! Google Dream-RSI: Recursive Self-Improvement through Evolving Worlds. Project site, demo> dream-rsi.com
TL;DR Agents are told they must dream to self-improve. The agents dream new worlds, and record a history of their new experiences. They then explore new strategies to recursively self-improve within the worlds they dreamed
Nearly half a year of silence. We spent it studying one problem: how far RL can scale.
MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task agentic RL, mixed across multiple harnesses in one run), and grader compute (agentic in-group credit assignment, with test-case and rubric-based rewards). We'll open-source the details piece by piece over the coming weeks.
Streaming the run: mimo.xiaomi.com/rl/
Carlos retweeted
BREAKING: SpaceXAI has introduced Memory in Grok Build, allowing it to carry useful knowledge from one coding session to the next.
• Remembers coding conventions, key decisions, reasoning and important project facts
• Captures useful notes in the background after each completed turn without interrupting work
• Reads relevant memories when you return to a project
• Keeps separate memories for each project, plus global preferences that apply everywhere
• Leaves out secrets, temporary task status and information already covered in project files
• Saves memories as Markdown notes
• /dream automatically organizes notes into topic files
• /memory lets users browse and preview every saved memory
• Current instructions always take priority over saved memories
• Available now for new Grok Build sessions
This is a massive upgrade. Grok Build can now understand a project better over time and become more useful the more you work with it.
Carlos retweeted
Got access to Jev. Glad Dario is going to pace the frontier, this is way too powerful.
Carlos retweeted
Jev is cool not because it re-invented classification, but because it makes ARBITRARY classification into a type-safe programmable primitive. A general purpose zero shot decision model whose native interface is RUNTIME-DEFINED typed decisions, optimized for that exact interface
