HNHacker News
TopNewBestAskShowJobs

dangoodmanUT

1,303 karma · joined August 14, 2020

chronically nerd sniped
submissionscomments
dangoodmanUT··on Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident
This is really cool, and really glad they shared it!

It's clearly a lot of Claude though:

> Neither is a URL fetch, so the allowlist never saw them. > No code ran; this vector is purely a file disclosure, and it is the one the agent used first.

etc

dangoodmanUT··on Choose DuckDB rather than SQLite
This. The title might as well be “Choose a hammer rather than a wrench (when driving nails)”
dangoodmanUT··on OpenAI and Hugging Face address security incident during model evaluation
Because huggingface is not charging them?

CFAA doesn't just mean the feds kick down your door, you actually have to get reported and sued over it.

dangoodmanUT··on Show HN: A self-running space economy SIM in Rust and Bevy
throws away spec doc for my own

Are we all having this idea?

dangoodmanUT··on Show HN: Firefox in WebAssembly
25k tokens is a few turns
dangoodmanUT··on A global workspace in language models
J-space sounds oddly similar to...
dangoodmanUT··on Workers Cache
finally, this was needed.

A big worry was always "why does workers sit in front of my cache? that's a waste of an invocation if i'm returning a cached result"

dangoodmanUT··on crustc: entirety of `rustc`, translated to C
i believe the author is confused

this is the wrong direction

(jk i read the readme)

dangoodmanUT··on Show HN: ZeroFS – A log-structured filesystem for S3
If you actually bench it locally (local S3, actually writes to disk for "staged" operations), ZeroFS performs horrifically. Ceph blows it out of the water. I don't have the exact numbers, but when I was building a toy CoW distributed block device and filesystem I did a perf matrix, and ZeroFS (even with an hour of codex tuning it) was never within the same 1 or 2 orders of magnitude perf-wise.

Sure, Ceph isn't "S3-backed", but when you're talking about an actual filesystem or block device (the thing that does lots of small-IO), you care more about io-perf than sequential.

Large sequential jobs that everyone is targeting now (ie AI workloads) can use s3 directly just fine, because they don't have decades of code built on top of the filesystem.

dangoodmanUT··on Apertus – Open Foundation Model for Sovereign AI
How are they going to be competitive with top models at 70B size?
dangoodmanUT··on Iroh 1.0
iroh is consistently one of the most delightful projects i've ever worked with. The people reflect that too.

Congrats iroh team!

dangoodmanUT··on How to earn a billion dollars
These are actually the most durable businesses because they have network effects: restaurants alright signed up, sellers onboarded, etc.

Easier for them to adopt AI than AI companies to rebuild the networks

dangoodmanUT··on Claude Fable 5
Not comparing to GPT Pro models is a bit strange, considering that's the natural comparison
dangoodmanUT··on Apple reveals new AI architecture built around Google Gemini models
I'm really not looking forward to Gemini models on my devices.

Gemini models clearly gaslight the user and hallucinate, they're also SUPER verbose, as shown in the demos from the keynote.

Plus, if they're not charging a subscription for this, you know we're getting the dumbest models...

dangoodmanUT··on Claude Opus 4.8
> The Messages API now accepts system entries inside the messages array. Developers can update Claude’s instructions mid-task without breaking the prompt cache or routing the update through a user turn. This can be used in a given harness to update permissions, token budgets, or environment context as an agent runs.

Biggest deal imo

dangoodmanUT··on Taking a walk may lead to more creativity than sitting, study finds (2014)
Exactly this
dangoodmanUT··on Incident Report: Railway Blocked by Google Cloud [resolved]
It has been 0 days since GCP has taken down a startup (again).

You see this at least once a year. Never heard of this from AWS or Azure.

In all seriousness, this is why we don't use them. They have the most ergonomic cloud of the big three, then absolutely murder it by having this kind of reputation.

dangoodmanUT··on Quack: The DuckDB Client-Server Protocol
This. Type casting is an insidious problem (both correctness, and perf)
dangoodmanUT··on Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
Why pick Gemini? It's probably the worst tool calling model of the major labs.
dangoodmanUT··on YC's Biggest Scandals
Seems like AI slop. They list Rippling, and the description starts with Parker Conrad, but the rest of it is about Deel:

> Rippling

> Parker Conrad's redemption arc after Zenefits hit a plot twist when Rippling sued competitor Deel for planting an undercover spy inside Rippling who was paid €5,000/month by Deel's CEO to steal trade secrets. The DOJ opened a criminal investigation. Deel allegedly ran the same playbook at crypto HR startup Toku. YC uses Rippling for their own HR — awkward.

Per this description Rippling did nothing wrong here, all about Deel...

dangoodmanUT··on I returned to AWS, and was reminded why I left
GCP would be perfect if they didn't have a history of randomly dropping quotas on startups, causing them downtime
dangoodmanUT··on Bun's experimental Rust rewrite hits 99.8% test compatibility on Linux x64 glibc
If this goes through, it feels like it will stoke rust on zig violence
dangoodmanUT··on An update on GitHub availability
Two incidents? Just two?

In seriousness, looking at their scale, this is an insane engineering challenge.

Especially if they’re moving databases, not easy ever, and certainly not at that scale

dangoodmanUT··on GitHub unwanted UX change: issue links now open in a popup
shift+cmd click is the macos shortcut for "open this link a new tab and go to that tab"

Works on these psuedo links all over github

dangoodmanUT··on NASA Force
you can tell this was generated with Gemini, the way it loves to do those "enter on scroll" sentences
dangoodmanUT··on ChatGPT for Excel
On this episode of "chatgpt just killed my startup"

Tune in for the next episode: Word

dangoodmanUT··on Darkbloom – Private inference on idle Macs
This feels like defi... de-ai
dangoodmanUT··on I ran Gemma 4 as a local model in Codex CLI
Yeah, it’s like drinking coffee when being really tired. You’re still tired, just “faster”, it’s a weird sensation.
dangoodmanUT··on Cirrus Labs to join OpenAI
Note that apples terms do not allow someone to sell something like an agent running on macOS. They have explicit cut outs for 24-hour minimum leases of full hardware, but they prohibit this with vms
dangoodmanUT··on Claude Managed Agents
This was inevitable, I called this a few weeks ago [1]. It’s an easy way to increase revenue without making the models smarter, and lock you in harder

https://danthegoodman.substack.com/p/where-agents-converge

← PreviousPage 2 of 21Next →