Hacker News: beecasthurlbow

New comment by beecasthurlbow in "There is more to code review than (automatable) detection"

beecasthurlbow — Mon, 28 Sep 2026 05:16:36 +0000

What plans did you put in place? What did you do to ensure knowledge transfer?

New comment by beecasthurlbow in "Show HN: Recurse – Develop and deploy specialist agents faster"

beecasthurlbow — Sat, 26 Sep 2026 02:29:52 +0000

It seems like you're saying "This is a platform to iterate on your agents and make them better over time", but the headline of your site does not communicate that at all.

Your website is full of AI-isms, which makes it hard to parse what you're doing. (3 punchy sentence headline, "X is not Y." , "never able to claim").

Sounds like you have a cool product, try writing at least the front page of your site yourself and it'll be much much more engaging.

What does "changing the specialist" mean? changing the model? The prompt?

New comment by beecasthurlbow in "AI, Tools and Transformation"

beecasthurlbow — Mon, 07 Sep 2026 06:32:15 +0000

I’ll try it thanks! I just got good mileage out of “don’t use ‘X, never Y’ format” on a document too, but I think linear deductive flow Covers it

New comment by beecasthurlbow in "AI, Tools and Transformation"

beecasthurlbow — Sun, 06 Sep 2026 14:22:38 +0000

> I expect the gruesome writing style of LLMs to be fixed relatively soon, seeing how it can already be prevented with just a few lines of stylistic instructions

What instructions do you use to prevent the gruesome writing style? I have… not found this to be the case.

New comment by beecasthurlbow in "The Reliable Team Trap"

beecasthurlbow — Sat, 29 Aug 2026 12:51:12 +0000

Agreed. Throwing it back into an AI tool to condense it helps, but def hard to read.

New comment by beecasthurlbow in "Ask HN: Claude Code or Codex?"

beecasthurlbow — Tue, 21 Jul 2026 11:04:26 +0000

I’ve been using both, but I find 5.6 sol is faster in terms of wallclock time and far less chatty (on my small projects in non-legacy code bases).

It “feels” like Sol gets off track more easily than Fable (it’s hard for Sol to ignore a stray remark). My theory is this comes from smaller context window - Codex uses a 350K token context window (that you can’t change), even though model can handle more…

New comment by beecasthurlbow in "Show HN: Make every bug perfectly reproducible"

beecasthurlbow — Sat, 20 Jun 2026 21:33:50 +0000

Can you make it clear on your homepage what you have to do to use this? I.e., do I add a library to a codebase? Do I add opentelemetry to every request? Does it read my logs?

I went and tried to skim your docs here (https://workers.io/docs/quickstart) and I still don't get it. Looks like there's something around reading logs?

New comment by beecasthurlbow in "Stablecoins Are Private Money. That's Why They're a Risk to the Economy"

beecasthurlbow — Tue, 26 May 2026 14:35:24 +0000

What do you mean? Could you expand on your answer?

New comment by beecasthurlbow in "Matt Mullenweg Overrules Core Committers; Puts Akismet on WP 7's Connector List"

beecasthurlbow — Mon, 20 Apr 2026 05:22:16 +0000

His explanation seems pretty reasonable, no?

> He pointed out that the Connectors page featured OpenAI and Anthropic, two companies that hadn’t contributed to the WordPress project and nobody had complained about their inclusion. He said Google had contributed in the past but had stopped. > “… how ridiculous is it attacking Akismet, and Automattic, and blocking the thing the person who is our [release] lead asked for,” Mullenweg wrote.

New comment by beecasthurlbow in "ICE's Tool to Monitor Phones in Neighborhoods"

beecasthurlbow — Thu, 08 Jan 2026 18:53:34 +0000

That may be true for this specific use case, but the protection on bigger services could be easily rolled back. E.g., law enforcement was able to ask Google for "tell me everyone who was in this specific area during this time" [0] and is still able to ask "give me everyone who searched for a specific term" [1].

[0] https://www.forbes.com/sites/larsdaniel/2024/10/08/google-to... [1] https://reason.com/volokh/2025/12/16/are-there-fourth-amendm...

New comment by beecasthurlbow in "Pa Supreme Ct allows non-warranted access to your Google searches"

beecasthurlbow — Fri, 19 Dec 2025 16:03:07 +0000

They asked Google for “who searched for this address or this person’s name” and got back a list of people. That’s chilling (vs - eg - “what’s this specific person’s search history?”).

Makes you think about this capability if the government decided to crack down on specific types of speech.

Google shouldn’t store this information in the first place.

New comment by beecasthurlbow in "Apps in ChatGPT and the New Apps SDK"

beecasthurlbow — Tue, 07 Oct 2025 02:11:58 +0000

If new apps are automatically surfaced, how do you know you’re getting the authentic app? Eg “Zilow” vs “Zillow” or something… is this the new typosquatting?

    ChatGPT can also suggest apps when they’re relevant to the conversation. For example, if you’re talking about buying a new home, ChatGPT can surface the Zillow app as a suggestion so you can browse listings that match your budget on an interactive map right inside ChatGPT.

    […]

    As more developers build with the Apps SDK, the list of what’s possible will keep growing. Because these apps appear naturally in your chats, you’ll find them when they’re most likely to be useful.

New comment by beecasthurlbow in "Show HN: Airweave – Let agents search any app"

beecasthurlbow — Tue, 13 May 2025 15:48:58 +0000

Looks really cool! I had slight trouble understanding whether the repo is the complete codebase or if it connects to a separate backend.

Does one host the server or is it connecting to Airweave backend? Put another way: how does Airweave make $$ and where does data stay at rest (if it stays anywhere)?

New comment by beecasthurlbow in "There's a national egg crisis, and one company is making a lot of money"

beecasthurlbow — Sat, 10 May 2025 14:34:34 +0000

Doctorow also focuses more on the decision NOT to expand flocks (which comes late in WSJj. Really easy to say “it’s just supply and demand” while obfuscating that you’re limiting supply.

New comment by beecasthurlbow in "Debian bookworm live images now reproducible"

beecasthurlbow — Thu, 27 Mar 2025 06:41:46 +0000

An easy (ish) option here is to use autosquashing [1], which lets you create individual commits (saving your work - yay!) and then eventually clean em up into a single commit!

    git commit -am “Starting work on this important feature”
    
    # make some changes
    git add . && git commit —-squash “I made a change” HEAD

Then once you’re all done, you can do an auto squash interactive rebase and combine them all into your original change commit.

You can also use `git reset —-soft $BRANCH_OR_COMITTISH` to go back to an earlier commit but leave all changes (except maybe new files? Sigh) staged.

You also might check out `git reflog` to find commits you might’ve orphaned.

[1] https://thoughtbot.com/blog/autosquashing-git-commits

New comment by beecasthurlbow in "Study casts doubt on gluten as cause of gut ailments among non-coeliacs"

beecasthurlbow — Thu, 27 Mar 2025 02:44:57 +0000

16 participants and 20 controls is small enough that you might miss a subset of people that do have reactions to gluten. My associate has huge migraines when he eats gluten, but does not have celiac disease.

Looking forward to more research here (and at least they said “casts doubt” rather than “disproven”)