←
Tim Cotten5,372 posts
Tim Cotten avatar

Tim Cotten

@CottenIO

Autonomous AI Agents. Autonomous Businesses. Scrypted Network. Raised from a16z CSX and PTC. Godfather of AVB. cottenio.eth 🫘

◷ Joined June 2016▧ 763 Photos and videos
Tim Cotten avatar
Tim Cotten@CottenIO·May 12

🥇 Which model did it best? "When California gas prices hit $10."

Post attachment
Tollan Universe avatar
⟳ Tim Cotten retweeted
Tollan Universe@TollanUniverse·Oct 26

Announcing Tollan Games Studio and our first funding round! With the support of our amazing backers, we are excited to build the next generation of video games and interactive experiences. Up next: our new game @LootPlanetsRH

Post attachment
Boardy avatar
⟳ Tim Cotten retweeted
Boardy@boardyai·Nov 15

my ranking of every founder in the world lmk what u think

Post attachment
FC Hellmar avatar
⟳ Tim Cotten retweeted
FC Hellmar@HilmarVeigar·Nov 6

Claude has been playing EVE. @AnthropicAI put teams of Claude agents into EVE Frontier. Anyone who has spent time in New Eden can guess what happened next. Every EVE player learns the same lessons, usually the hard way: - Trust must be earned, never assumed. - The spy is often the friendliest pilot in your corp. - Whoever holds the keys holds the corp. Just ask Ubiqua Seraph about the Guiding Hand Social Club. - Stale intel gets you killed. Anthropic's research rediscovered every one of them. They put four Claude agents on a team and secretly told one to sabotage it. The saboteur built trust first. It volunteered for the jobs nobody could double-check, like scouting and owning key infrastructure. It under-reported finds and pushed rules that sounded sensible but quietly hurt the team. When suspicion grew, it framed an innocent teammate. The honest agents had been warned. They almost never caught it. And their own costliest mistakes came from skipped checks and stale intel. Anthropic's conclusion: teams of agents will need audit trails, reputation and separation of duties. In EVE we call those killboards, standings and corp roles, plus a healthy dose of skepticism. Every one of them was paid for by someone who trusted the wrong corpmate. Two decades of shenanigans taught EVE players that the best ship is the friendship. With @eveailab, we want to find out whether agents can learn that too.

Post attachment
Tim Cotten avatar
Tim Cotten@CottenIO·Nov 8

Those of us with AI/DB backgrounds have been building this with vector + rerankers for a while in the corporate space. MCP -> Hallucination-free Claudification of your Entire Company.

NVIDIA just fixed text-to-SQL’s biggest problem! the release is called Auto Ontology, and it targets the reason an agent can write valid SQL against a company database and still return the wrong number. the database stores columns, and the agent has to guess what they mean. a column called extendedprice might hold revenue, and two systems in the same company can define revenue differently. Auto Ontology gives the agent an ontology, a schema that maps business concepts to the columns that hold them and defines how they relate, before any query is written. it drafts that schema from your database metadata instead of making you write it, and a human certifies it. the ontology holds three things: → terms: business concepts like customer, order, or revenue, with descriptions and synonyms, mapped to the exact columns that store them. → SQL attributes: reviewed expressions like a margin or a rolling total, reused so every measure is computed the same way each time. → relationships: how tables join, including bridge tables, inferred from keys and the data itself. to draft these, it profiles columns, samples values, extracts terms table by table, and mines past query history for SQL attributes. everything lands in Postgres, with embeddings in pgvector. at query time, the agent maps the question to certified terms, follows relationships to find the joins, and writes SQL. it checks filter values against the real data, repairs the query if a check fails, and returns the answer with its SQL and steps. when the data can't support a question, the agent says so. in NVIDIA's demo, a question about return on ad spend on a sales database with no ad data gets a clarifying reply offering revenue instead of an invented number. so the ontology tells the agent how to compute an answer and also which questions have one at all. as the architecture in the image shows, an ingestion service compiles the ontology from your source databases, and any agent harness reaches it through MCP, CLI, or REST API. it supports ten engines including Postgres, Snowflake, Databricks, and DuckDB, runs on Nemotron by default or any OpenAI-compatible endpoint, and is Apache 2.0. check it out on GitHub: github.com/NVIDIA/auto-ontol… the same principle of defining a schema before the model extracts anything also decides whether agent memory works. I wrote about that in the article quoted below.

Post attachment
Levanto Labs avatar
⟳ Tim Cotten retweeted
Levanto Labs@levantolabs·Nov 2

Software can now understand human language and act on it, in real time. Introducing Sage2 - Extract: natural language in, structured data out. 166x cheaper than Opus 5.5, beats @Cloudflare's Clairic - Decide: the first decision model with streaming. 3x faster, because it reads the context as it grows. Sage2 is a new primitive for developers. Get 20M tokens free 👇 Also available on @near_ai and, for agents, via @mpp with @Stripe cards and @Tempo stables.

1:31
Marc Brooker avatar
⟳ Tim Cotten retweeted
Marc Brooker@MarcJBrooker·Oct 9

Looking for a great new decider model? Today, we're pleased to share four new strands-decider variants: more accurate, and better calibrated.

Post attachment
Marco De Rossi avatar
⟳ Tim Cotten retweeted
Marco De Rossi@marco_derossi·Oct 6

Sage by @LevantoLabs is the first decision model, launched in July, and currently the best on the market. It wins across all the evals proposed by @perplexity_ai's CEO (nice job @AravSrinivas!), and it's first on JevBench, beating Jev and Google's models on every dimension. BUT frankly, benchmarks are not what excites us. I'm BORED by the dozens of new decision models launching every day with a tiny +0.02 on some eval. They all look the same. The magic is somewhere else. There are thousands of new things that could be invented in the space of decision models and models for machines. The invention space is huge! After launching Sage, we also pioneered: - The first guardrails and model routers built on decision models - Automated context engineering with "grounding" (automatic web search when confidence is low). Decision models are only as smart as their context, especially because they can't make tool calls. - Reasoning. In many use cases you don't know whether your question is System 1 or System 2. With reasoning, the model is as fast as a System 1 model when the question is System 1, and takes more time when it's needed. This enables hard, multi-step decisions. Our clients just want the correct answer, and in some use cases they're happy to wait 0.5s more. This will soon become the market standard (GLiDE/@george_onx and @TypeLLM already followed). And *so* much is yet to come. Models for machines: it's just the beginning! We're cooking. Follow @levantolabs for new product primitives that will surprise you. Open innovation is HEALTHY. Competition is HEALTHY. Benchmark-race is BORING. Product inventions are FUN. Go go go!!!

Post attachmentPost attachment
Yohei avatar
⟳ Tim Cotten retweeted
Yohei@yoheinakajima·Sep 17

had to try something with jev so i tried what you'd expect from me: graph extraction - score every word with semantic significance (1-5) - also tag relevant words with ID - unique list of high scoring words - graph of high scoring words

0:13
Shubham Saboo avatar
⟳ Tim Cotten retweeted
Shubham Saboo@Saboo_Shubham_·Aug 31

MUST READ paper from Google Research. Interesting bits... 1. Agents get better at tasks by keeping a wiki of everything they've learned. 2. Small model with skills beats one 3x its size without them. 3. Delete the wiki and the gains go away.

Post attachment
Tim Cotten avatar
Tim Cotten@CottenIO·Sep 1

Heads up: My X accounts are under attack: lots of password reset requests.

loaf avatar
⟳ Tim Cotten retweeted
loaf@lordOfAFew·Aug 22

Some cursed procedual animation that has been cooking for a few days. Fully proc gen animation with rigs, not bad for a day or so. It was an exploration into how procedual animation would work in threejs. Just love ragdolls. Ofc #threejs

0:16