gtirloni
Re:Show HN: HackerBooks – HackerTube, but for books mentioned on HN
on Sunday November 01, 2026 @01:08PM (#50328034)
It's the same harness but in Claude Desktop (which now integrates Chat/Work/Code), you can easily install some plugins for web design, etc. Not that you can't in the TUI but in the GUI it's a few clicks away.
Re:AI Isn't Replacing SREs. It's Deskilling Them
on Friday October 30, 2026 @08:43PM (#50312082)
SRE has been around for at least a decade or more.
Re:Ask HN: What's it like working at Google nowadays? Core teams like ...
on Friday October 30, 2026 @06:02PM (#50310738)
Are you qualified to judge in all those areas? I too look at websites Claude builds in amazement but I'm sure that's a lot of crap underneath.
Re:Bunny CDN Security Incident
on Friday October 30, 2026 @05:51PM (#50310634)
> Last week, one of our infrastructure providers reported unauthorized access involving third-party server management software. One of our CDN nodes, located in Armenia, was hosted on a server supplied by this provider
Are they talking about physical security? Someone grabbed the server, etc?
Colocation providers usually don't care about security beyond that, or has that changed?
Re:Show HN: 10x faster, 3x cheaper ETL
on Tuesday October 27, 2026 @07:54PM (#50267575)
Why was SQL slow? Where did processing shift to?
Re:OLED iPad Mini
on Monday October 26, 2026 @12:05PM (#50246111)
I see what you did there!
Re:Lula wins election after final votes tallied
on Monday October 26, 2026 @11:55AM (#50245910)
They explain why you should refrain from posting about politics here, unless there's an angle that makes it interesting for the HN crowd.
Re:PaperPilot – Zero-Cloud, Pure-Rust PDF Engine with WASM and MCP
on Monday October 26, 2026 @11:42AM (#50245672)
LLMs will miss a lot of edge cases. This is critical for a library that parses PDFs. Ask it to review the code for issues and by the 20th time you ask, it still will find issues. How's that faster (or safer)?
I use AI heavily but it's not this omnipresent deity that knows everything at all times.
Re:Anthropic S-1
on Monday October 26, 2026 @11:36AM (#50245553)
It's high-risk in that it's proven to not work anymore. Scale isn't a differentiator or won't be in the short term.
Meanwhile, everyone else is working on making these models more useful through a ton of ecosystem around them.
I don't see how the frontier labs will have any control over that to deliver on what investors expect. As mentioned in another post here, if they could, they would already be spawning hundreds of companies to diversify their reach but they aren't, because this era of AI is awesome but still doesn't allow a few individuals to replace millions of others that easily (or efficiently).
Re:Anthropic S-1
on Monday October 26, 2026 @11:30AM (#50245442)
Their own system cards say it's not.
This cyber apocalypse narrative is what they tell government and markets.
Re:Lula wins election after final votes tallied
on Sunday October 25, 2026 @09:03PM (#50237710)
> submitted the news too and it got flagged
Please review the HN guidelines:
Re:A Mathematician Reads the AI Future
on Sunday October 25, 2026 @02:33PM (#50234582)
Useful new questions and useful new or novel directions? What's the signal-to-noise ration there?
I think AI is going to improve a lot of things but people thinking the future is on auto-pilot now are delusional.
Re:A Mathematician Reads the AI Future
on Sunday October 25, 2026 @02:30PM (#50234550)
Public-funded research is still a thing though.
Re:A Mathematician Reads the AI Future
on Sunday October 25, 2026 @02:28PM (#50234530)
Do you mean without proofs as a what assigns value to the thesis? I think AI doesn't make them optional at all.
Hanami
Tell HN: PagerDuty incident causing repeated alerts/escalations
Re:Tesla Roadster
on Thursday October 15, 2026 @09:48PM (#50112811)
> It challenges the limits of design, engineering and physics to deliver an expertly crafted extra-terrestrial vehicle.
closed tab. thanks.
Re:GitHub's new dashboard experience now the default
on Thursday October 08, 2026 @10:00AM (#50005901)
I think it shows "100% test coverage" isn't testing what matters otherwise AI would get signals back telling it things are bad so keep working until they are good. I don't have a solution for this but more and more tests isn't the answer. I had AI create a small-ish CLI the other day and it added >2k tests and things still felt garbage. Now imagine that at GH.com scale. AI won't solve it with the current paradigms. I would love if someone could point me at good research in this area (not prompt evals).
Re:GitHub's new dashboard experience now the default
on Saturday October 03, 2026 @07:57AM (#49943481)
I suspect it's the huge amount of requests they get and more so now with AI. Some estimates put traffic at 3-5x what it was just a year ago.
If GH.com is anything like GHE, the number of moving parts is staggering.
Re:GitHub's new dashboard experience now the default
on Saturday October 03, 2026 @07:47AM (#49943399)
What's the relevant party that is having a bad experience due to lack of IPv6?
Re:GitHub's new dashboard experience now the default
on Saturday October 03, 2026 @07:44AM (#49943372)
You do experience it when using it. What HN does the most is complaint exactly about the experience.
Re:GitHub's new dashboard experience now the default
on Saturday October 03, 2026 @07:43AM (#49943365)
Could you be more specific?
Re:GitHub's new dashboard experience now the default
on Saturday October 03, 2026 @07:43AM (#49943362)
Is this last update one of those worse experiences?
Re:Claude Opus 5.5
on Wednesday September 23, 2026 @01:35AM (#49812039)
The hype/degrade/hype marketing cycle that Anthropic uses to cycle between Fable/Opus or Opus/Sonnet releases is too obvious at this point.
Opus 5.5 will be great for 2-3 weeks than the nerfing starts. They give out some extra credits. It keeps degrading Opus until it's unusable . By that time they are ready to release Fable 6. Which also is great for a few weeks, and so on.
Re:GPT-6 Sol and Luna
on Wednesday September 23, 2026 @01:07AM (#49811881)
What's the relevance of the pelican benchmark when models probably saw it during training? Didn't OpenAI stop testing against SWE-Something because it was tainted?
Re:Xiami Mimo 2.6 Live Training Dashboard
on Wednesday September 16, 2026 @10:44PM (#49735823)
They think they have the special sauce. Even if they do, what would they get in return for doing that?
Re:Why is the x86 undefined instruction called ud2? Why 2?
on Sunday September 13, 2026 @03:56PM (#49688017)
I recently had to debug builds that failed randomly and a ud2 from V8 was there waiting for me.
Re:GPT-6 Astra
on Saturday September 05, 2026 @02:41PM (#49579411)
By in context learning do you mean latent space?
Re:GPT-6 Astra
on Saturday September 05, 2026 @02:34PM (#49579339)
When threatened with physical or social harm. What they think in their little heads though :)