konaraddi

Another 2-5 years from now, it may even become accessible to most people (current barriers being cost and technical expertise, bottleneck is cost).

Discussed yesterday https://news.ycombinator.com/item?id=49920932

Storm of Steel - Written by a WW1 soldier about his experiences. His Wikipedia page is fascinating.

https://en.wikipedia.org/wiki/Ernst_J%C3%BCnger

There will be demand for both

Woah the A19 Pro is 5th, that’s bonkers! It’s used in an iPhone and its power consumption is lower than chips intended for desktops.

How long would the phone get security updates?

Also looks like they sell cellular plans too https://plans.minimalcompany.com/#plans

Depending on the context, circuit breakers

There’s an unlocked developer edition.

Crosspoint links to it at https://crosspointreader.com/devices

Paywalled

> On September 4th the Bureau of Labour Statistics reported that the American economy added 162,000 jobs in August, far above expectations.

Good news that ought to be taken with a pinch of salt given how the current administration responds to unfavorable BLS data -

> On Friday, August 1, [2025] President Trump fired Dr. Erika McEntarfer from her role as the Commissioner of the Bureau of Labor Statistics (BLS). In social media posts announcing and confirming her firing, he said that he believed the jobs report released by the agency earlier that day included numbers that were “rigged in order to make the Republicans, and ME, look bad.”

https://www.epi.org/policywatch/firing-bls-commissioner-erik...

Does it purge passwords from memory on vault lock?

Regardless of one’s political slant, it is clear that Flock is giving experiences and objects of value to public servants with clear intent to retain or obtain their business. I’m not familiar with the legal definition of bribery but Flock’s behavior certainly quacks like bribery.

My current and previous employers have mandatory employee training that covers and curbs this kind of behavior. I suspect, and hope, Flock is going to learn why.

I think the more coding agents the better, more ideas mixing and borrowing that’s yielding improvements across actively developed agents and different tradeoffs being made. From the article, Ramp’s Inspect was made with frontend in mind and is particularly good with Ramp internal tooling. Looks like it’s not open source? https://inspect.ramp.engineering/auth/

The blog post doesn’t have much further material or at least not before the paid envelope.

Some thoughts I have -

> 1. Local machines are limited in how many agents they can run. Ramp found third-party products below expectations; they liked Claude Code on day 1, but were constrained by only being able to run one or two sessions on local machines.

I haven’t seen this constraint? I only started using Claude Code ~4 months ago so maybe it was different before.

> 3. Need for remote dev environments. As Ramp scaled, so did the complexity, and with it there was more work at the intersection of systems, like debugging backward compatibility, and broken API contracts. The solution was to create remote dev environments.

This seems disjoint, not sure I follow how remote dev environments was necessary to solve this or why remote dev environments would be the only solution?

> Hooking up Inspect to the data sources that engineers would browse with the same tools seems to be a key difference between Inspect and third-party AI harnesses.

You can do the same with third party AI harnesses, I guess we’d have to see what Inspect does that’s better than providing MCPs, CLIs, scripts, etc. to an agent.

Should be titled “Why Ramp built its own in-house coding agent, Inspect” (that’s the title of the post at the time of this comment)

This doesn’t seem written for kids though?

Great read that brings some rigor (or at least cites rigor) to what has otherwise been anecdotal.

> then what is the path for one to become an expert so they can effectively use these tools?

The article briefly mentions guard rails and I think on the same note we need the AI agents we use for coding to encourage learning and comprehension in its users. Right now it’s completely voluntary and on the onus of engineers to put in the effort to learn since, as the article states, the friction that led to some degree of required learning is gone.

Nice to see herdr support. The docs seem to imply it only works with vercel’s AI gateway? I guess it cant be configured to use another provider?

Link to the preprint https://www.medrxiv.org/content/10.64898/2026.07.22.26358689...

In practice, full access to your machine is okay as long as there are safeguards and the expected outcomes are clear with a well defined path to said outcomes that aren’t overly ambitious. Otherwise, for ambitious goals or YOLO one shot attempts, eliminating opportunity for capability misuse is critical (e.g., sandbox).

Sounds like toolbox or distrobox for Mac!

Objectively terrible policy for ethics, public safety, and, selfishly, the American economy. Immigrants contribute to economic growth and are less likely to commit crimes are well established facts. It’s the 21st century, we have the internet and education is accessible, but instead of recognizing and championing the vital role of immigrants in America’s rise to power, here the nation moves to hurt itself for some misguided anti immigrant ideology.

A lot of comments here are about the issues with the analysis in OP’s post but much of them are “a distinction without a difference” with respect to the broader conclusion. When we look at purely cost and performance (setting aside privacy) then it’s better for individual devs to pay for hosted then for self hosting. Employers are paying for tokens on the job and most devs are finding the $PREFERRED_PROVIDER’s $20/$100/$200/month subscription sufficient outside of work. Most devs don’t fall in the conditions under which running local models make sense purely on the basis of cost vs performance.

More critically, in practice, setting up local models seems more like a hobby, an educational exercise, or an act of privacy control than it is for cost cutting or productivity.

There’s so many ways, many redundant, to set up agents for software development that beyond personal/team/org needs+tastes, I need to look into setting up some benchmarks to evaluate what set up is optimal or whether the differences are even worth it.

> the NSF funds approximately 25% of all federally supported basic research conducted by the United States' colleges and universities.[5][6] In some fields, such as mathematics, computer science, economics, and the social sciences, the NSF is the major source of federal backing

https://en.wikipedia.org/wiki/National_Science_Foundation

EDIT: other folks beat me to it

That’s awesome! Do you know how it compares to Handy? Handy is open source and local only too. It’s been around a while and what I’ve been using.

https://github.com/cjpais/handy

Thanks! I want to do something similar to your LLM suggestion, the endgame is tooling for forums and individuals to improve the quality of discourse. More broadly, I think LLMs and recent advancements now make it possible to assist with self improvement (e.g., see former startup Humu’s nudges but for everyone instead of just B2B)

In single-turn use, yeah, but across dozens of turns there's probably value in optimizing the output.

Btw your point lands just as well without "Cute idea, but" https://odap.knrdd.com/patterns/condescending-reveal

> applying this compression algorithm at scale may significantly relax the memory bottleneck issue.

I don’t think they’re going to downsize though, I think the big players are just going to use the freed up memory for more workflows or larger models because the big players want to scale up. It’s a cat and mouse race for the best models.

Full quote from Fuller for others

> You do not have the right to eliminate yourself, you do not belong to you. You belong to the universe. The significance of you will forever remain obscure to you, but you may assume that you are fulfilling your significance if you apply yourself to converting all your experience to highest advantage of others. You and all men are here for the sake of other men.

Nvm! I used an artist link but it needed a track link

> couldn't load artist — Spotify API is temporarily unavailable