HNHacker News
TopNewBestAskShowJobs

Esophagus4

1,353 karma · joined February 11, 2025

submissionscomments
Esophagus4··on Uber torches 2026 AI budget on Claude Code in four months
I think the lack of evidence for LLM productivity is not an indictment on LLMs… it’s an indictment on the industry still having no real way to measure developer productivity in general.
Esophagus4··on I benchmarked Claude Code's caveman plugin against "be brief."
Yeah there are similar “joke” tools / languages that found their friendly audience for a time.

I like when programmers do creative, goofy stuff rather than spending all their time cranking out sterile soulless SaaS.

It’s what separates us from the machines. For now :)

https://github.com/ajalt/fuckitpy

Esophagus4··on HashiCorp co-founder says GitHub 'no longer a place for serious work'
Oh man, what could go wrong.

Edit: to be clear for anyone reading, don’t do this, it’s a really bad idea. You need to patch your stuff, even behind a VPN. If you’re unsure, just google: “examples of security breaches of unpatched software behind VPNs”

Esophagus4··on HashiCorp co-founder says GitHub 'no longer a place for serious work'
I’ve argued the opposite most of the time in build vs buy. Buy in almost every case unless it’s a real competitive advantage to you.

I know developers love to build, but do you think:

1) self-hosting git provides any competitive edge to the business over letting someone manage it?

2) it provides so much value that you’re willing to fund engineers to build, secure, support this on an ongoing basis?

I’ve found the answer to those is No in both cases.

The same reason you wouldn’t build your own internal chat tool, you’d use Slack. And you wouldn’t bother self-hosting your own Jira or documentation.

Code hosting is code hosting, there’s no difference where it's hosted. There’s no slowdown in delivery with using GitHub - their March uptime was 99.5% which annoys some commenters but it’s fine. That’s 45 minutes downtime per month which is tolerable.

You would spend way more effort and money building a jenky self-hosted solution to end up with a worse result.

Esophagus4··on Warp is now Open-Source
Hey Aloke!

Thanks for the tip, I’ll give this a try and see how it goes.

Esophagus4··on Warp is now open-source
I really like Warp.

I’ll admit the UI has changed a lot recently and I find it more intimidating than when I was using it a year ago, so I mostly use Ghostty now.

Esophagus4··on I bought Friendster for $30k – Here's what I'm doing with it
That… actually seems kinda fun…

I know this wasn’t the point I was supposed to take from your comment but I’m liking this idea

Esophagus4··on Show HN: A free ESG stock screener that publishes its losses and methodology
The question was percentage of net worth :)

That will tell me how confident you are.

$10k out of $500k would say you’re toying around.

$10k of $20k seems like you believe it works.

Esophagus4··on Show HN: A free ESG stock screener that publishes its losses and methodology
One last question - as a percentage of your net worth, how much of your own money have you put into the stock picks generated through this analysis?

I have a feeling I know the answer, but wanted to check.

Esophagus4··on Show HN: A free ESG stock screener that publishes its losses and methodology
A question I have: do you have a background in capital markets?

Because what it looks like is you asked Claude to create a stock picking newsletter based on signals that retail commonly thinks are bleeding edge but institutions have been using for two decades and probably don’t give much edge anymore (AI analysis of news sentiment…)

And you backtested from 2012-2025, one of the longest bull runs in history. Of course your strategy of “buy NVDA” will win in that window.

Which makes me wonder: have you ever worked at a hedge fund?

I have to say I’m tempted to subscribe and have Claude manage an imaginary portfolio based on your recommendations and publish that. Because to be frank, I’m fairly confident your recs won’t generate alpha.

Esophagus4··on Jumping into cold water can stop your heart
The internet is a content beast, and the beast must be fed.
Esophagus4··on Nobody Got Fired for Uber's $8M Ledger Mistake?
I have been a part of over-built solutions.

It’s usually because executive management bakes hyper growth into the assumptions because they really want the biz to grow, then it becomes marching orders down the chain as it gets misinterpreted in a game of corporate telephone.

“We need to design this for 1b DAUs”

Then 1) that growth never happens and 2) you end up with a super complicated solution

Instead, someone needs to say, “Hey [boss], are you sure we need to build for 1b DAUs? Why don’t we build for 50m first, then make sure it’s extensible enough to keep improving with growth”

Esophagus4··on Nobody got fired for Uber's $8M ledger mistake?
Hate to say it but kind of a lousy article... zippy writing but lots of Monday Morning Quarterbacking for something the author doesn't seem to show much knowledge of. Maybe this is his style to gin up subscribers, but I'm not a fan.

> But nobody was optimizing for cost. They were optimizing for their next promotion. Each rewrite was a new proposal, a new design doc, a new system to put on a resume. The incentive was never to pick the boring, correct choice — it was to pick the complex, impressive one.

...I guess it could be possible nobody thought about cost at all, and this was all misaligned incentives and resume-driven development, but I find that kind of hard to believe? As someone who has made cost mistakes in the cloud, this claim seems a bit silly.

Not to detract from his experience, but I didn't actually see much payments experience at all on his resume, so I'm curious why he's branding himself as a payments guru. Kind of tech content creation fluff, I guess.

Esophagus4··on Claude Code to be removed from Anthropic's Pro plan?
Is it? I’m curious because I thought they were raising prices to pay for exorbitant training costs, not because subscribers are expensive on a unit basis.

I thought inference was cheap so there was little marginal cost of a new subscriber.

Esophagus4··on Claude Code to be removed from Anthropic's Pro plan?
A few enterprise customers I know are upgrading to the higher plan now that their limits have been nuked.

I imagine Anthropic is trying to see how many users they can push to higher tiers with these new squeezes.

I hate to say it but I imagine it will work.

It’s going to suck for me, because I had gotten used to ridiculously cheap tokens, but I guess the era of subsidized tokens is over.

Esophagus4··on Claude Code to be removed from Pro Tier?
> $20/month was just too big a loss to sustain.

Is there any marginal cost associated with a new subscriber?

I have always heard inference is cheap and the cost was in training, so I assumed any subscriber was making them money, just not enough to cover their insane fixed costs.

But I am just guessing.

Esophagus4··on Claude Code to be removed from Anthropic's Pro plan?
> Claude has become practically unusable for Pro users in the past few days. The Opus 4.7 blew through an entire 5 hour limit in one question and didn’t even finish answering it

Glad I’m not the only one!

I’ve been limited so often this week I’ve setup half a dozen token compression tools in my workflow and had to do a crash course in token optimization.

Of course, it seems to only slightly delay the inevitable and doesn’t really solve the problem.

Esophagus4··on Framework Laptop 13 Pro
> shouting out specific team members who did the designs

Inside the case somewhere on mine there was a list of all the names of the people who worked on it. Was pretty cool.

Esophagus4··on Laws of Software Engineering
> All of this was driven by imagined scale rather than real measurements

Yes. When I was a young engineer, I was asked to design something for a scale we didn’t even get close to achieving. Eventual consistency this, event driven conflict resolution that… The service never even went live because by the time we designed it, everyone realized it was a waste of time.

I learned it makes no sense to waste time designing for zillions of users that might never come. It’s more important to have an architecture that can evolve as needs change rather than one that can see years into the future (that may never come).

Esophagus4··on OpenAI ad partner now selling ChatGPT ad placements based on “prompt relevance”
Because everything is securities fraud: https://www.bloomberg.com/opinion/articles/2019-06-26/everyt...
Esophagus4··on Claude Token Counter, now with model comparisons
It got limited while it was reading the repo before starting to fix, but yes you’re right. I think I was in auto mode or at least approving all the exploration.
Esophagus4··on GitHub's Fake Star Economy
Big Heads
Esophagus4··on Claude Token Counter, now with model comparisons
Didn’t realize that, thank you!
Esophagus4··on Claude Token Counter, now with model comparisons
Oh nice! Thank you, I will definitely give this a shot.

I was looking at tree-sitter myself for this task.

Esophagus4··on Claude Token Counter, now with model comparisons
“Ok Claude, I bet you can’t hit the usage limit in one shot… let’s see what you got you little token gremlin”

;)

I just asked it to do a security analysis in a subagent of an unmaintained browser extension and then go fix vulnerabilities it found so I can use it without worrying.

Esophagus4··on Claude Token Counter, now with model comparisons
Anyone have good tips or resources on token management best practices? Because I’ve hit the limiter with one single prompt now on Opus 4.7.

What I’m reading so far seems to be:

-selective use of models based on task complexity

-encoding large repos into more digestible and relevant data structures to reduce constant reingesting

-ask Claude to limit output to X tokens (as output tokens are more expensive)

-reduce flailing by giving plenty of input context

-use Headroom and RTK

-disable unused MCP, move stuff from CLAUDE.md to skills

But I’d love to learn if anyone has any good tips, links, or tools as I’m getting rate limited twice a day now.

Esophagus4··on Ex-CEO, ex-CFO of iLearningEngines charged with fraud
Very cool website. Looking through a few of those examples, holy Jesus there is a lot of fraud out there.

Fun read.

Esophagus4··on Ex-CEO, ex-CFO of iLearningEngines charged with fraud
And before that, dot-com: https://www.forbes.com/2001/01/09/0109zapata.html

Some things will never change

Esophagus4··on Airline worker arrested after sharing photos of bomb damage in WhatsApp group
> Radha Stirling, chief executive of London-based advocacy group Detained in Dubai, said Dubai police had "explicitly confirmed they are conducting electronic surveillance operations capable of detecting private WhatsApp messages."

Whoa.

Esophagus4··on Silicon Valley is turning scientists into exploited gig workers?
“I am, somehow, less interested in the weight and convolutions of Einstein’s brain than in the near certainty that people of equal talent have lived and died in cotton fields and sweatshops”

-Stephen Jay Gould

← PreviousPage 5 of 25Next →