Hacker News: jmtulloss

New comment by jmtulloss in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

jmtulloss — Wed, 03 Jun 2026 22:21:13 +0000

Is your argument that $1500 / mo is too much? Why would the engineering team not be more rigorous in their model selection given a constraint?

New comment by jmtulloss in "Anthropic confidentially submits draft S-1 to the SEC"

jmtulloss — Mon, 01 Jun 2026 16:40:40 +0000

Why do you think this? Confidential filings before an IPO are standard practice.

New comment by jmtulloss in "Anatomy of the .claude/ folder"

jmtulloss — Sat, 28 Mar 2026 04:40:00 +0000

Exactly this. If there is some nuance in the article vs what Claude can tell you, then that's worthwhile. This article is just generated with a specific prompt on style but very little content editing. What's the point? It's like posting the results of a Google search. The prompt would have been more interesting.

It's not against the rules to post AI slop here, and I don't necessarily think it should be. But I do wonder how we value written content going forward. There's value to taste and style and editing and all the other human things... there's very little value in the actual words themselves. We'll figure it out.

New comment by jmtulloss in "GitHub is once again down"

jmtulloss — Tue, 24 Mar 2026 23:00:38 +0000

The best stretch Github ever had was post-acquisition when Nat Friedman as CEO.

New comment by jmtulloss in "LaGuardia pilots raised safety alarms months before deadly runway crash"

jmtulloss — Tue, 24 Mar 2026 21:34:56 +0000

FWIW the whole group received permission to cross. The instructions were to "Truck 1 and company", not just Truck 1

New comment by jmtulloss in "How does misalignment scale with model intelligence and task complexity?"

jmtulloss — Tue, 03 Feb 2026 01:26:43 +0000

The comments so far seem focused on taking a cheap shot, but as somebody working on using AI to help people with hard, long-term tasks, it's a valuable piece of writing.

- It's short and to the point

- It's actionable in the short term (make sure the tasks per session aren't too difficult) and useful for researchers in the long term

- It's informative on how these models work, informed by some of the best in the business

- It gives us a specific vector to look at, clearly defined ("coherence", or, more fun, "hot mess")

New comment by jmtulloss in "List animals until failure"

jmtulloss — Mon, 02 Feb 2026 05:20:50 +0000

Yes, it’s not a hill I’m willing to die on. It’s a hill I’m willing to defend until the cause is lost.

New comment by jmtulloss in "List animals until failure"

jmtulloss — Sun, 01 Feb 2026 05:27:22 +0000

This is what I'm saying. Chipmunks are not squirrels. I will do my best on this hill.

LLM-as-a-Courtroom

jmtulloss — Tue, 27 Jan 2026 18:32:36 +0000

Article URL: https://falconer.com/notes/llm-as-a-courtroom/

Comments URL: https://news.ycombinator.com/item?id=46784210

Points: 74

# Comments: 30

New comment by jmtulloss in "Believe the Checkbook"

jmtulloss — Sat, 20 Dec 2025 04:08:01 +0000

Obviously novel problems require novel solutions, but the vast majority of software solutions are remixes of existing methods. I don’t know your work so I may be wrong in this specific case, but there are a vanishingly small number of people pushing forward the envelope of human knowledge on a day-to-day basis.

New comment by jmtulloss in "Rivian Unveils Custom Silicon, R2 Lidar Roadmap, and Universal Hands Free"

jmtulloss — Fri, 12 Dec 2025 03:33:33 +0000

The reason for this is Rivian and Tesla bet big on software defined platforms… ie every piece of hardware talks to a small number of central computers instead of many independent systems. This gives them a huge leg up in developing software than can actually take all the available input and use it to control all aspects of the vehicle.

Downside is all the buttons are on a screen. But I’ve grudgingly decided it’s worth it for software upgrades.

New comment by jmtulloss in "Rivian Unveils Custom Silicon, R2 Lidar Roadmap, and Universal Hands Free"

jmtulloss — Fri, 12 Dec 2025 03:29:11 +0000

The current Gen 1s will start beeping at you if they can’t see the lines. If you don’t take over quickly it will start slowing down and beeping very insistently.

New comment by jmtulloss in "Rivian Unveils Custom Silicon, R2 Lidar Roadmap, and Universal Hands Free"

jmtulloss — Fri, 12 Dec 2025 03:16:51 +0000

Not only is Rivian betting on an integrated platform being important for their own cars long term, they’ve also essentially sold that portion of their business to VW. They are investing in the software platform for a lot more cars than just the rivian branded ones.

New comment by jmtulloss in "The profitable startup"

jmtulloss — Sat, 01 Nov 2025 04:49:40 +0000

Linear is a venture funded company

New comment by jmtulloss in "Ground stop at JFK due to staffing"

jmtulloss — Fri, 31 Oct 2025 04:07:43 +0000

A lot of commenters are focusing on the legalities and likelihood of backpay, which is relevant but I tend to agree with you… it’ll get paid because it’s in the interest of both parties to pay their employees what they’re owed.

We’re staring down the barrel of two missed paychecks though. If you're living paycheck to paycheck you’re getting desperate. If you’re living with about 1 month of emergency buffer… that buffer is one paycheck away from gone. It’s a cash flow issue

New comment by jmtulloss in "Ground stop at JFK due to staffing"

jmtulloss — Fri, 31 Oct 2025 03:42:12 +0000

And the republicans could just vote to change the rules of the senate.

The out of power party gets a little veto power here. The republicans know the day will come they want that, so they won’t change the rules even though they have the power to do so (theoretically… there are republicans that will never compromise on this). Unfortunately they can’t get on the same page with their lame duck leader

New comment by jmtulloss in "Claude Skills"

jmtulloss — Thu, 16 Oct 2025 18:51:35 +0000

My interpretation of the parent comment was that they were loading specific curl calls into context so that Claude could properly exercise the endpoints after making changes.

New comment by jmtulloss in "Embracing the parallel coding agent lifestyle"

jmtulloss — Fri, 10 Oct 2025 09:01:32 +0000

It doesn’t have access to your repo when the agent is running (unless you give it internet access and credentials). The code is checked out into the sandbox before it’s let loose.

New comment by jmtulloss in "Embracing the parallel coding agent lifestyle"

jmtulloss — Fri, 10 Oct 2025 04:30:25 +0000

Good point. The environments I’ve set up have been pretty easy but I’ll admit that at first I was very annoyed that it couldn’t just use a pre-existing GitHub action workflow.

Edit: environment setup was also buggy when the product launched and still is from time to time. So, now that I have it set up I use it constantly, but they do need to make getting up and running a more delightful experience.

New comment by jmtulloss in "Embracing the parallel coding agent lifestyle"

jmtulloss — Fri, 10 Oct 2025 04:16:45 +0000

Why aren’t more folks using Codex cloud? Simon’s post mentions it, but the vast majority of comments are talking about parallel agents locally or getting distracted while agents are running.

Personally I’ve found that where AI agents aren’t up to the task, I better just write the code. For everything else, more parallelism is good. I can keep myself fully productive if many tasks are being worked on in parallel, and it’s very cheap to throw out the failures. Far preferable imo to watching an agent mess with my own machine.