Latent Node

@tom_doerr You can do the same with this app - cited-report.vercel.app

Monitors and optimizes content for AI-powered search engines github.com/ai-search-guru…

@__RobertG__ @Teknium Default seems to work fine actually.

Can someone who is a seasoned Hermes Agent user recommend a good memory setup? There are a number of options (Honcho, OpenViking, Mnemosyne, etc.) and I have no idea which one to choose. I just want something that works well and that I can run locally. @Teknium, any advice?

@headinthebox I remember those days, having a good MSDN collection was enough documentation we needed to code.

This is like in the olden days not allowing humans to use StackOverflow (if anyone remembers what that was ;-)

@secemp9 I think it will end up like @magic_labs too - huggingface.co/blog/codelion/…

they seem to have paid ppl to post about this + not planning on OSS just like magic.dev and seems to be just hot air, so essentially, this is bs, next question

@brian_armstrong Perhaps next time do not use AI to draft such an email - …ptive-classifier-ai-detector.hf.space/?id=91fba7b584…

This is an email I sent earlier today to all employees at Coinbase: Team, Today I’ve made the difficult decision to reduce the size of Coinbase by ~14%. I want to walk you through why we're doing this now, what it means for those affected, and how this positions us for the future. Why now Two forces are converging at the same time. We need to be front footed to respond to both. First, the market. Coinbase is well-capitalized, has diversified revenue streams, and is well-positioned to weather any storm. Crypto is also on the verge of the next wave of adoption, with stablecoins, prediction markets, tokenization, and more taking off. However, our business is still volatile from quarter to quarter. While we've managed through that cyclicality many times before and come out stronger on the other side, we’re currently in a down market and need to adjust our cost structure now so that we emerge from this period leaner, faster, and more efficient for our next phase of growth. Second, AI is changing how we work. Over the past year, I’ve watched engineers use AI to ship in days what used to take a team weeks. Non-technical teams are now shipping production code and many of our workflows are being automated. The pace of what's possible with a small, focused team has changed dramatically, and it's accelerating every day. All of this has led us to an inflection point, not just for Coinbase, but for every company. The biggest risk now is not taking action. We are adjusting early and deliberately to rebuild Coinbase to be lean, fast, and AI-native. We need to return to the speed and focus of our startup founding, with AI at our core. What this means To get there, we are not just reducing headcount and cutting costs, we’re fundamentally changing how we operate: rebuilding Coinbase as an intelligence, with humans around the edge aligning it. What does this mean in practice? - Fewer layers, faster decisions: We are flattening our org structure to 5 layers max below CEO/COO. Layers slow things down and create coordination tax. The future is small, high context teams that can move quickly. Leaders will own much more, with as many as 15+ direct reports. Fewer layers also means a leaner cost structure that is built to perform through all market cycles. - No pure managers: Every leader at Coinbase must also be a strong and active individual contributor. Managers should be like player-coaches, getting their hands dirty alongside their teams. - AI-native pods: We’ll be concentrating around AI-native talent who can manage fleets of agents to drive outsized impact. We’ll also be experimenting with reduced pod sizes, including “one person teams” with engineers, designers, and product managers all in one role. In short: AI is bringing a profound shift in how companies operate, and we’re reshaping Coinbase to lead in this new era. This is a new way of working, and we need to leverage AI across every facet of our jobs. To those who are affected I know there are real people behind these decisions — talented colleagues who have poured themselves into this company and our mission. To those of you who will be leaving: thank you. You’ve helped build Coinbase into what it is today, and I am sincerely grateful for everything you've done. All impacted team members will receive an email to their personal account in the next hour with more information, and an invitation to meet with an HRBP and a senior leader in your organization. Coinbase system access has been removed today. I know this feels sudden and harsh, but it is the only responsible choice given our duty to protect customer information. To those affected, we will be providing a comprehensive package to support you through this transition. US employees will receive a minimum of 16 weeks base pay (plus 2 weeks per year worked), their next equity vest, and 6 months of COBRA. Employees on a work visa will get extra transition support. Those outside of the US will receive similar support, based on local factors and subject to any consultation requirements. Coinbase prides itself on talent density. Our employees are among the most talented people in the world, and I have no doubt that your skills and experience will be highly sought after as you pursue your next chapters. How we move forward To the team that is staying, I know this is a difficult day. We’re saying goodbye to colleagues and friends you've been in the trenches with. But here’s what I want you to know as we move forward together: Over the past 13 years, we have weathered four crypto winters, gone public, and built the most trusted platform in our industry. We’ve made it this far by making hard decisions and by always staying focused on our mission. This time will be no different – nothing has changed about the long term outlook of our company or industry. And most importantly, our mission has never been more important for the world. Increasing economic freedom requires a new financial system, and we’re building it. The Coinbase that emerges from this will be more capable than ever to achieve our mission. Brian

@nectarios Can you do a SPV can let others in as well please.

I have an opportunity to invest in Anthropic at a 900b valuation. What do you think? Worth it?

@jiazhi_yang2024 @chris_j_paxton @KnightNemo_ Great work, we also recently worked on a world model using mobile game play videos - x.com/latent_node/st…

The world model community has been waiting for something like this 👇 nano-world-model repository by @KnightNemo_ — clean, minimal, hackable. github.com/simchowitzlabp…

@yminsky Also related - dev.to/mame/which-pro…

I am also interested in this, I think the key is to make types the independent variable. Same model, tasks, and tools; vary prose docs vs JSON Schema vs richer ADTs/refinement/effect/session types. Measure task success, malformed calls, semantic misuse, recovery from type errors, cost, and unsafe actions. The important distinction is “well-typed but wrong” vs actually correct.

So, I really want someone to do a study on the effectiveness of types for agents. Studying the same question with humans is absurdly expensive, but agents provide a new way of asking the question. Is anyone working on this?

@sudip_r0y What exactly does it do? Do I give an intial dataset and you evolve it to be bigger and better across some metric?

You don't have a model problem. You have a data problem. Most fine-tuning teams already know this. Almost none have the tooling to fix it systematically. Today that changes. Together AI fine-tuning is now live inside Adaptive Data. Dataset shaping to deployed model. LoRA to 100B+. One platform.

@hallerite Yes, we already did something similar in a more controlled setting - x.com/latent_node/st…

can a model trained on a pre-1930 corpus of knowledge discover information theory from first principles is the most realistic thing to test here

@HarveenChadha AWS? Is it cost prohibitive for Indian companies to just use and secure clusters on hyper scalers?

We are either too optimistic or too pessimistic, why can’t we have nuanced takes anymore? “deploy at scale” ?? on what hardware exactly ????

@SIGKITTEN always felt a bit like the perpetual motion machine

what happened with that thermodynamic computer thing

@WanderCoventry @kalomaze We actually tried something similar recently - x.com/latent_node/st…

this is a pop sciency version of a continual learning evaluation if you're going to go the route of "pretrain on limited data and see if it can bootstrap from natural interaction", a more practical thing would probably be like, train only up to ~2014, "can it teach itself Rust?"

@xwang_lk isnt deepseek the deepseek code or you think they will make a specific model for coding?

When DeepSeek Code?

@tszzl Just do caffeinate -d

people are walking around with their laptops slightly ajar to keep their agents running

@kalomaze We actually looked at something similar in a more controlled setting recently - x.com/latent_node/st…

@dosco thank you

@latent_node Large Language Monkeys: Scaling Inference Compute with Repeated Sampling arxiv.org/abs/2407.21787

sampling + verification is the key to really unlocking the true potential of LLMs so many breakthroughs like Google AlphaCode etc is powered by this. with a good verifier cheaper models can outperform expensive ones. deepseek with 5 samples costs 10 usd and performs better.

@yminsky Very interesting idea, but why won't you do it yourself instead of just building custom UI. I assume the rest of the stack is also going to get easier to build and manage.

So, are things like twenty.com the future of enterprise software? Rather than have consultants come in to customize your enterprise system, use agents to build custom UIs on top of a carefully engineered core.