calufa

LLMs are hungry for tokens. Every day I see more startups claiming token usage at 50-100k per month. You can always brute-force your way in - just see HuggingFace's recent attacks.

If throwing more money at inference while accumulating compounding technical debt is the new norm, then we are not solving the problem, and the solution space is already covered.

Perhaps there are marginal gains at the expense of quadrillion-params LLM models with 10x the cost and energy. We are simply making inefficiency more expensive, camouflaged by VC money and great marketing.

If that is not plateauing, then I guess I will have to reconsider what plateauing means.

As LLM coding agents plateau— at least for the average engineer without tens of thousands of dollars or swarms of agents to run —I’d say that, from here on it’s going to be about ASICs, specialized LoRA/or-equivalent models, or a Ruby on Rails for LLM context engineering and orchestration, which LangChain and others seems well position, including Google as they own the entire stack. LLM free lunch has been over for a while, perhaps since the ReAct loop, and has been official since Ilya mentioned it at NeurIPS.

I feel the most exciting development these days is self-evolving agents. Especially if you have a way to verify their outputs with a formal system, or with a system developed since the 60s by armies of PhDs.

DeepMinds Gnome is a good example, where they use DFT to verify outputs. Approximating NP-problems is always fun for those who dare.

I am also building in this space. Its a mix between HPC, AI, and hard science. Pretty fun compared to waking everyday to LLM news that seem more like marketing stunts.

Better technology cannot compensate for poor product design. Two weeks' worth of tokens sounds like tens of thousands of dollars by the time it is done. Wouldn't it be better to hire someone who knows what they are doing, get it right, and teach the other engineers why and how? Tech dept and product dept creeping in on every LLM loop, compounding.

Location: San Francisco, CA

Remote: Yes, open to remote or hybrid

Contract: Yes

Technologies: LLMs, agentic systems, RAG, semantic search, recommendation systems, computer vision, workflow automation, Python, TypeScript, React, Node.js, PostgreSQL, Kubernetes, Docker, AWS, GCP

Résumé/CV: linkedin.com/in/carloschinchilla | github.com/calufa | medium.com/@calufa

Email: [email protected]

Staff AI Engineer / former CTO with 20+ years of software experience and 10+ years building AI systems across LLMs, agentic workflows, semantic search, recommendation systems, computer vision, generative media, and infrastructure.

I have built and led multiple zero-to-one AI products, including a WhatsApp finance copilot, invoice automation platform, AI-powered budgeting app, dental computer-vision product, text-to-video AI platform, recommendation infrastructure, and semantic search systems.

I was previously CTO at YC and Techstars-backed startups, and two companies I helped build were later acquired by OpenAI and LDC/private equity.

Recently, I have been focused on AI-native workflow platforms, company-brain systems, agentic search, LLM tool use, sandboxed execution, structured outputs, evaluation, human-in-the-loop workflows, and AI systems that turn messy business processes into reliable software.

Currently it doesn't look at the robots.txt file. I had taken note of this, and will be added in future releases. Thanks for the suggestion.

Here is a sample code of a 1 depth scrape:

https://github.com/calufa/tales-templates/blob/master/core/s...

This is the api call to start the scraper on twitter:

http://localhost:8080/start?process=tales.scrapers.LoopScrap... -template tales.templates.FirstDepthTemplate -threads 2 -namespace com_twitter -baseURL twitter.com

It will basically go through all the links it finds, that can be millions of links. You can also tell it to ignore certain links using regular expressions or via tales java apis.

"... and vector('king') - vector('man') + vector('woman') is close to vector('queen') [3, 1]. You can try out a simple demo by running demo-analogy.sh..."

I downloaded the code but I dont understand how to get queen as a result. I tried submitting king - man + woman, but the bin dont understand it.

For those who want to use a java based solution, I invite you to check out my open source block tolerant (IP Blocking) web scraper that runs on top of aws and rackspace, called Tales. Tales is designed to be easy to deploy, configure, and manage. With Tales you can scrape 10s or even 100s of domains concurrently.

https://github.com/calufa/tales-core

Take a look at Tales.

Tales is a block tolerant web scraper that runs on top of aws and rackspace. Tales is design to be easy to deploy, configure, and manage.

https://github.com/calufa/tales-core

I am just enabling. For me it's not the "what". Its the "who".

this is why jcoulds will be supported soon.

-- well yeah, its a cpu thing, we may need to lower the kb size on the imgs that made up the sprites, and less fps I guess... we need to do more optimization...

maybe some framerate issues, I am aware I need to compress more the imgs to improve it... I will work on that... -- thanks!

...like everything is running slow because of cpu (framerate problems), or is more like the character moves too slow...?

we are 2 friends from Costa Rica trying to build a game engine. The server is made in node.js, all the actionscript code is made by us with no dependency and we sync the sprites and config files using dropbox. -- Feedback is always welcome...

Provisioning is not that hard, nor scaling -- you can always create a image and create servers from that image. In my case, I usually create a server that listens to git and the rest is synced by some program who is also listening the folder where the git repo is.

Heroku looks cool, but I am used to compile things...

I use rackspace and its very cool. Rackspace is fast and simple, and is also cheap. Their server runs fast, and smoothly. AWS is sometimes too complicated, lots of config, lots of choices, lots of weird price changes -- I am talk about the recent spot instances weird pricing fluctuations, and other wierd episodes they have had. Unless you know exactly what you are doing scaling in AWS will take more time and effort -- Unless you are Zynga, and you need a stupid amount of server which almost noone of the server providers except amazon have, or you dont want to deal with relational db scaling problems, or other of the expensive and specific service that amazon offers I dont see why complicate things in the "building stage". AWS is too complex for my use cases, and my software is usually transparent to the server where he is running, so I can always port my code. Rackspace API is stable and it talks JSON, which is cool because my frontend and backend talks javascript.

I guess this question is too open... the answer will always be, depends on what you are building..., and you amount of experience on the field... In my case several 8gb rackspace servers with a cost of 10 dollars a day seems to work well for collecting and crunching gigabytes of data.

Carol Bartz drama was hilarious, but I must agree that she really sucked! its sad because Yahoo devs are making cool things... is just that execs seems focused on building something "better" than AOL, and, as you know just by mentioning AOL things start smelling funny.

I would like to do something with Twillio, unfortunatelly I cant find a idea...

- abstraction from a design level

- introduction and importance of cpu, memory, harddrive, network and gpu from a design perspective

- teach how to represent data with objects

- scalability from a design perspective. why performance tuning will safe you ass in the long road -- explain data-driven-development

- the power of data and analytics visualizations

- agile, and why iterating means move fast, and why being dynamic is important. why quick sprints are better than product releases (3 months of dev without exposing anything to the user = risk)

- were we are now in this field, and what others have done and are doing - i mean Ted-like inspiration

- its important to understand that design patterns exists and what they do. but are not really necessary at this point because design patterns are hard things to crack for people new to programming. yet very powerful way to abstract the functionalities of the app, and thats why is important to know what they are. for small projects the use of strong design patterns seem sometimes a little exaggerated. for new people design patterns can set the bar really high

we use node. we sync our servers with dropbox and git. we use hummingbird for real time analytics and mixpanel. we are 2 guys from Costa Rica (http://www.costarica-discover-it.com/images/caribbean2_nov30...). we have been working on this for the last 2 months... thanks!

internet individual instruct inform inspire

http://www.youtube.com/watch?v=0BHPtoTctDY&feature=playe...