lexh
Re:Claude's Load-Bearing Seams
on Wednesday September 23, 2026 @06:24PM (#49823417)
They missed the first legitimate use case for infinite scroll.
Re:GPT-6 Astra has gained the ability to drive a car
on Wednesday September 23, 2026 @11:55AM (#49818017)
So... competitive with Uber, in other words?
don't think it's that deep mate. just sloppy wording on GP's part.
Well... since o1 (Sept 2024), most models generate a "hidden" thinking trace before the visible answer... surely you have seen this by now: "Wait, that's wrong...", "Ah, now I have the full picture...". The model prunes dead ends when it composes the final answer.
Demanding sources for this is odd. It's literally been a headline feature of every frontier model for two years.
I guess you are "technically correct" that no model can "un-emit" tokens... but I don't think that is what anyone was saying or an interesting point to make.
Edit: see also this recent post, which details another place where revisions can happen, upstream of the reasoning token emission:
Re:Ternlight – 7 MB embedding model that runs in browser (WASM)
on Tuesday July 07, 2026 @04:53AM (#48815191)
Similar idea here that may be of interest: SQLite DB on static host via HTTP range + WASM.
Re:Taking a walk may lead to more creativity than sitting, study finds
on Tuesday May 26, 2026 @12:35PM (#48282075)
Re:Show HN: DAC – open-source dashboard as code tool for agents and hu...
on Saturday May 02, 2026 @06:53AM (#47985264)
Consider adding that snazzy gif in the README to the docs landing page. I went straight to the docs and then hunted for a screenshot to no avail.
Re:The Zig project's rationale for their firm anti-AI contribution policy
on Thursday April 30, 2026 @04:43PM (#47967970)
But... this particular project does have such automation in place? It isn’t hard to find:
https://codeberg.org/ziglang/zig/src/branch/master/.forgejo/...
Re:"Over 1.5 million GitHub PRs have had ads injected into them by Cop...
on Monday March 30, 2026 @12:44PM (#47576627)
https://copilot.microsoft.com/shares/RviQKF1om6oxZY2pENL6c
Sample size is 2 now!
Re:Vercel's CEO offers to cover expenses of 'Jmail'
on Tuesday February 10, 2026 @10:59AM (#46961621)
Isn’t part of Vercel’s value proposition a robust global CDN in front? Seems quite a bit different than one sweaty VM in Helsinki.
Re:Who needs Graphviz when you can build it yourself?
on Wednesday October 29, 2025 @05:37AM (#45744567)
This is a great write up.
I wonder if any of these techniques turn up in whatever the magic sauce is in D2’s TALA layout engine, which is in a league of its own IMO.
Re:I want everything local – Building my offline AI workspace
on Friday August 08, 2025 @08:28PM (#44843041)
The current SOTA closed model providers are also all rolling out access to their latest models with better pricing (e.g. GPT-5 this week), which seems like a confounding factor unique to this moment in the cycle. An API consumer would need to have a very specific reason to choose GPT-4o over GPT-5, given the latter costs less, benchmarks better and is roughly the same speed.
Re:My 2.5 year old laptop can write Space Invaders in JavaScript now (...
on Tuesday July 29, 2025 @09:22PM (#44730126)
To be a little more fair... that example is tidily slotted into the EXAMPLES section, under the heading "You can extract images from a video, or create a video from many images".
I don't think most people read the man pages top to bottom. And even if they did, then for as much grief as you're giving ffmpeg, llm has an even larger burden... no man page and the docs weigh in at over 8k lines.
I get the general point that ffmpeg is a powerful, complex tool... but this is a weird fight to pick.
Re:Seven replies to the viral Apple reasoning paper – and why they fal...
on Saturday June 14, 2025 @08:37PM (#44279788)
Use the debatably intelligent machines for this sort of question not Google.
It seems “Yud” here is a shorthand for Yudkowsky. Hinted by the capitalization.
Prompt tricks Apple Intelligence into turning Writings Tools into a chatbot
Re:Trump Taps Palantir to Compile Data on Americans
on Friday May 30, 2025 @02:04PM (#44138609)
Why is this flagged? Seems to fit the submission criterion of "anything that good hackers would find interesting" and "gratifies intellectual curiosity" pretty cleanly... e.g. government technology contracts and data analysis, privacy and surveillance, a major tech company and its business practices, the intersection of technology and public policy, etc.
Re:Yagri: You are gonna read it
on Thursday April 24, 2025 @12:22AM (#43779236)
It is Postgres specific, but I’ve gotten a lot of mileage out of the advice in this article:
Re:We replaced our React front end with Go and WebAssembly
on Monday February 10, 2025 @11:05PM (#43008824)
I think some of it is shown on this page:
Re:I got OpenTelemetry to work. But why was it so complicated?
on Friday January 10, 2025 @12:46PM (#42657885)
Gee whiz is this person is in for a treat when they discover the joys of OpAMP https://github.com/open-telemetry/opamp-spec/blob/main/speci...
Turtles all the way down.
Re:Show HN: Go Plan9 Memo, Speeding Up Calculations 450%
on Friday October 18, 2024 @11:20AM (#41880231)
A bit over my head, but I enjoyed the way the writing brings us along for the ride.
This can’t be the first pass someone has made at something like this, right? There must be literal dozens of SIMD thirsty Gophers around. Would a more common pattern be to use CGO?
Re:When new hires get paid more, top performers resign first
on Friday March 29, 2024 @03:02PM (#39867734)
What line of work is full of former programmers?
Re:Show HN: Rem: Remember Everything (open source)
on Thursday December 28, 2023 @04:27PM (#38798848)
The impression I was left with is that this tool would write things to disk. It would be helpful to know how that data is stored. I wouldn’t want my password manager OCR’d and then sitting in plain text on disk for example.
Re:Show HN: Rem: Remember Everything (open source)
on Wednesday December 27, 2023 @09:45PM (#38789424)
“pretty scary stuff” indeed!
This would inevitably end up ingesting secrets, right? Like say from my password manager? Or API keys in my terminal?
Lots of ways for this to go sideways even if the data stays local.
What’s the plan there?
All the staff at my local coffee shop ask “for stay or for takeaway?”
They never deviate from this exact script and I find it grating every single time. Coffee is decent though so I let it slide.
Edit: “local” meaning Southern California.
Re:Home Assistant blocked from integrating with Garage Door opener API
on Wednesday November 08, 2023 @08:16AM (#38189902)
Oh, data collection. And subscriptions.
This makes sense (and myQ’s privacy policy is a nightmare: https://www.myq.com/privacy-notice) but I’ve never understood how this particular bit of data is valuable to anyone. Any ideas?
Re:Using spaced repetition systems to see through a piece of mathematics
on Tuesday October 17, 2023 @05:58PM (#37922182)
> Perhaps it is the article On Sense and Reference by Gottlob Frege?
>
> http://www.scu.edu.tw/philos/98class/Peng/05.pdf
Re:Anti-Anti-Adblocker uBlock filter to get rid of the annoying YouTub...
on Saturday October 14, 2023 @09:05PM (#37885831)
> You're telling me i provided $14/m in ad revenue? Of course not.
Do you really think Google just set the price arbitrarily? That would be surprising.
My impression has always been that ad free tiers are actually less profitable for video providers.
Re:GitHub code search is generally available
on Monday May 08, 2023 @04:56PM (#35866961)
Fantastic. Love the functionality on public GH and always find myself missing it at work.
Re:GitHub code search is generally available
on Monday May 08, 2023 @04:16PM (#35866489)
Will this make it to GH enterprise eventually?