So is nuclear annihilation. Yet, here we are.

> "I occasionally think how quickly our differences worldwide would vanish if we were facing an alien threat from outside this world." -- Ronald Reagan at the United Nations [0]

We are going to be fine as long as we remember to be nice to each other, starting towards the people who are adjacent to us.

[0] https://youtu.be/dYiUI6y1nKg?si=agkJpCEZj3m_WZz0&t=915

I wanted to demonstrate capacity (how well it does a thing) instead of capability (which things it does, like drawing a pelican on a bicycle with SVG or solving a Rubik's Cube). To understand how LLMs solve math, look at the simplest case of multiplication. I deconstructed and classified the thinking token output. It is very important that model training yields thinking token output that structurally follows an observe, orient, decide, act (do the multiplication), and observe again loop.

[0] https://adamsohn.com/reasoning-grid/

A probability grid of chain-of-thought, read through Boyd's OODA loop lens [0]

[0] https://adamsohn.com/reasoning-grid/

We can't trust Wikipedia, but still, in 2022, they put New Orleans at #8 with homicide rate. [0]

[0] https://web.archive.org/web/20240106080401/https://en.wikipe...

This makes sense.

I lived for several years in New Orleans, behind Wagner's in the Bywater. In 2022, it was ranked the 8th most dangerous city in the world. The gunfire was constant. Anyone who knows that corner knows the Family Dollar was so riddled with bullet holes that they eventually stopped repairing them. I'd be enjoying my morning coffee in my backyard, sitting on my bench with the neighbor's calico meowing at me, when fully automatic gunfire would ring out. I'd go to the Facebook group page, where people with military or gun experience would identify the type and caliber of the weapons involved. Then came the pictures of people's cars sprayed with bullet holes, and a story about someone lying in bed when a bullet whizzed over them and hit the opposite wall.

That intersection has cameras everywhere! The police already know what happened. If someone wasn't murdered it would hours before they would come out and look.

When I first moved there I lived in mid-city by 12 Mile Limit. Before I arrived, there was a triple homicide. Then there was a double homicide. The building on the corner had video of everything. They ended up towing the owner of the building's truck because it was evidence. She went to the impound to get it back because the bullet hole was from the previous triple homicide.

During these incidents, which are often (getting better over the last couple years), hundreds or thousands of people can hear them. The sound of fully automatic guns can carry for blocks. Being able to handle all the calls focusing on the few that arrive first likely will improve the service.

Comments URL: https://news.ycombinator.com/item?id=49188069

Points: 1

# Comments: 2

I can't justify spending $1k - $2k a month for real time options data and compute for what is in my 401k. I guess the question I have is would your tool help me trade these strategies and more important test them on a few hundred a month?

[0] https://github.com/adam-s/alphadidactic

Location: South America (US Citizen)

Remote: Yes

Willing to relocate: Yes

Technologies: TypeScript, JavaScript, Python, PHP, React, React Native, Svelte, Express, Bun, Angular, GraphQL, D3.js, visx, Backbone, jQuery, LangChain, Mastra, FastAPI, pandas, scikit-learn, Optuna, Chrome Extension API, Playwright, Electron, Stagehand, browser-use, Web Audio API, WebRTC, WebSockets, PostgreSQL, TimescaleDB, MySQL, MongoDB, Redis, AWS, EC2, S3, Lambda, Docker, Git, LLM agent design, agent evaluation, reinforcement learning, browser automation, MCP

Résumé/CV: Ask via email

Email: [HN username]@gmail.com

GitHub: https://github.com/adam-s

Website: https://adamsohn.com

Currently in South America and planning my move back to the US once a role is secured (whether in San Francisco or another city) to avoid relocating twice.

Due to high interest in my work with recursive self-improving coding agents, I've shared an example repo at https://github.com/adam-s/agent-tuning. I'm always open to discussing how I optimize agents for complex, repetitive workflows.

I bring 13 years of full-stack UI development experience alongside deep expertise in browser automation and agents, which I've been engineering since 2018. This blend makes me particularly strong in QA automation engineering, browser automation, and complex frontend architecture.

Notable projects include custom legal document management dashboards and a drag-and-drop CRM email builder for social marketing campaigns. As a consultant and full-time engineer, I’ve led 0-to-1 product development across fintech, streaming, real estate, edtech, marketing, and media. Having worked at companies ranging from a 130-person AI organization to a scrappy 7-person team, I thrive most in fast-paced, high-ownership environments.

Remote: Yes

Willing to relocate: Yes

Technologies: TypeScript, JavaScript, Python, PHP, React, React Native, Svelte, Express, Bun, Angular, GraphQL, D3.js, visx, Backbone, jQuery, LangChain, Mastra, FastAPI, pandas, scikit-learn, Optuna, Chrome Extension API, Playwright, Electron, Stagehand, browser-use, Web Audio API, WebRTC, WebSockets, PostgreSQL, TimescaleDB, MySQL, MongoDB, Redis, AWS, EC2, S3, Lambda, Docker, Git, LLM agent design, agent evaluation, reinforcement learning, browser automation, MCP

Résumé/CV: Ask via email

Email: [HN username]@gmail.com

The best data visualization of LLM model evaluation you will see today, https://adamsohn.com/reasoning-grid/.

Currently in South America and planning my move back to the US once a role is secured (whether in San Francisco or another city) to avoid relocating twice.

Due to high interest in my work with recursive self-improving coding agents, I've shared an example repo at https://github.com/adam-s/agent-tuning. I'm always open to discussing how I optimize agents for complex, repetitive workflows.

I bring 13 years of full-stack UI development experience alongside deep expertise in browser automation and agents, which I've been engineering since 2018. This blend makes me particularly strong in QA automation engineering and complex frontend architecture.

Notable projects include custom legal document management dashboards and a drag-and-drop CRM email builder for social marketing campaigns. As a consultant and full-time engineer, I’ve led 0-to-1 product development across streaming, real estate, edtech, marketing, and media. Having worked at companies ranging from a 130-person AI organization to a scrappy 7-person team, I thrive most in fast-paced, high-ownership environments.

https://github.com/adam-s

https://adamsohn.com

> I have concerns that you'll have a job in a year

Me too because I might be the best TypeScript coder on Earth and there is no demand for those skills. I'm doing a pivot.

[0] https://en.wikipedia.org/wiki/Computer_(occupation)

Exactly as we don't write machine code letting the compiler do that, now and in the near future we won't be writing high level programming language code. We are moving towards working on a higher level of abstraction.

When I ask a frontier model to write a loop 10 different ways in Python and TypeScript and test the performance of each using a 1,000,000 iterations, it isn't creating cognitive debt. For the time being, I'm still racking my brain asking the question, how does garbage collection affect the performance.

[0] https://en.wikipedia.org/wiki/Panic_of_1873

Researchers showed that when language models are penalized for using specific terms during reasoning, they automatically adapt by substituting alternative words and double meanings to secretly encode their thinking while keeping their chain-of-thought readable and effective. [0]

By baking in the OODA loop early, the models are capable of solving much more complicated problems. If the know solved problems are similar for any reason to an unknown problem, because it can validate and error correct, it can solve unknown more complicated problems.

[0] https://arxiv.org/abs/2506.01926

I won't get into the metaphysics of reasoning, however, the Sonnet is using an OODA loop. The difference which hasn't been gapped is that human reason and imagination (in the sense of Mr. Rogers' Neighborhood) can predict the consequences of the actions we take.

This ability to loop is much, much wider in Opus 5 than Opus 4.. I had to strain to get Opus 4. to do the wider OODA loop but Opus 5 does it out of the box. I needed to throw out all existing instructions, skills, guidance, moving from 4-* to 5.

[0] https://adamsohn.com/lambda-variance/

1. Ask Claude Code or coding agent to research the internet, documentation, and Github for examples and learning working with similar problems.

2. Make the ten best examples of solving the problem based on the research.

3. Run each against the database enough times (100, 1000, or 10,000,000 depending) to empirically prove which is optimized. You can set other criteria based on your knowledge.

4. ???

5. Profit

The point is, it is cheap to research combing through 1,000s of examples and learnings and test the best and most relevant.

A couple of days ago, something interesting happened. The agent works in an iteration loop where each iteration is an endpoint. I let it run overnight. In the morning it was still cranking away even though it had finished all the API endpoints. It had found a changelog from one of the companies listing every single feature and bug, and decided on its own to implement every item as an iteration.

We are 2 to 3 months away from coding agents replicating solving the edge cases of most SaaS applications.

Can you explain this more, especially why SQLite is best at OLTP and what happens at scale?

We know that mild stress can narrow focus and help learning. "Neural connections do form when you struggle." [0] A little stress is not only good but necessary for learning while a lot of stress causes a breakdown. The trick is being able to judge the stress level of the student and every person is different.

The idea of using some type of bio metric data from EEG or blood pressure sensors will help determine a little struggle from a lot of struggle in formative assessment.

[0] https://www.youtube.com/watch?v=wh0OS4MrN3E

At that point they had ~24 employees. He said his interest was crowdsourcing and thought most of the engineering effort would go toward the crowdsourced translation, but at that time, it was being handled by just two employees.

They brought on two prominent consultant researchers, leaders in the field of language learning and linguistics. The first question they asked the consultants was which part of speech should they present to the learner first. The consultants didn't have an answer. They decided to dedicate engineers to collecting data in order to answer that question.

A big problem with edTech is that we don't know.