trueno

i've never known what to think about brave because it was being pitched by cryptocurrency bros so i've always ignored its existence. who are these guys and is it genuinely good software?

what's the diff between lite and full? i dont even remember what i use on safari, wipr or something. mostly use firefox but sometimes i casually just let things launch in safari

i think a lot of us are kind of sitting back and seeing what dark horse rises up. it's such a non-deterministic outputting technology that's still in discovery mode and the resources expenses/constraints are outta control, the companies leading the charge are eating themselves and can't guarantee jack squat. down in the trenches people have built these things up to be critical dependencies in either their day to day life or their work, my eyes are mostly glazing over hearing about how people are using claude to do whatever grand array of things with no oversight. the way we benchmark this shit is all over the map, the goalposts are just teleporting randomly at this point.

my claude usage has drastically dried up as i've personally realized the real bottom of this stuff is always gonna be genuinely learning and becoming excellent at a thing. i think claudes not bad for helping me get through early stages of that process, and for actual work i think claudes great for just ripping out something im too lazy to do, but something i know so well that i can catch him slippin. absolute coinflip on if it's worth the pain, many times now ive said "i shouldve just done this myself".

i've got my fingers crossed for like llm's to reach some sort of proverbial opus 4,5 territory here. even if thats gonna cost me a bit in hardware, that's kind of my personal bench mark for "good enough, i'm unplugging from all this craziness".

one thing is for sure, anthropic needs to stop adding _features_. claude code or vscode extension was their bread and butter reliability that garnered them a lot of goodwill from people who were willing to pay good money for a good service. seeing them launch their design thing just has me rolling my eyes. they're kind of microsoft'ing themselves here by trying to do too much, and they'll end up delivering a lot of subpar services that aren't best-in-class at any one thing. we're already seeing that i think.

> Everybody is building their own llm-wiki systems these days

there is a dark side to this. my coworker is insistent that his variant of this is going to become the teams backbone and i can't get him to stop even when i showed him a page of beyond wrong answers. he straight up doesn't understand that having a knowledge base != claude now sees all of it at once and can consider the endless breadth and shades of gray that make up human decisions. he's 100% convinced that claude grepping through the files is foolproof and won't miss any details lol

i personally just stopped messing with grand knowledge base ideas and these techs. i think everyone's shooting a lil too high and can't fully define what exactly they're after.

so i stepped back and i keep claude there for a very black and white need. claude's there to speed up stuff in domains i know well so i can guardrail him with massive success and have him code pieces im simply too lazy to code myself or alley oop something im struggling with. in a tortoise and the hare parable kind of way im the only guy here who isnt getting huge gotcha holes from AI in the solutions im delivering. all polished with the same attention to detail ive always had. i've just found these grand wiki everything ideas are just not yielding what people think they're yielding. for whatever reason i'm still the meatware layer thats a better index in the end if ive done my homework. perhaps something is lost when we cede a huge chunk of our journeys to seek information. i've still yet to be impressed by any "claude tied all these things together and found this insight this is insane" moments, every single time ive pointed out that any of that could've been a report.

i mean the whole thing is prob vibe coded. this was actually an exact thing i tinkered with when i first got a claude account. thought hey what if something easy like streamlit ergonomics for golang. gave up on that pretty quickly, it was one of those early "im gonna do something so big because im king of the world now" journeys that helped me learn where the limits of AI really is. with that said id love to see more gui developments in go. im actually not against AI helping speed this up, i just want people to be forthcoming about it. I need to know that they know what they're providing and what they're talking about.

but yeah i went thru the repo and the site and saw like one screenshot of like one component. i really dont think a guy who really actually cared about delivering something like this would kneecap its own success with a lack of screenshots for a GUI solution. that's beyond funny.

as for fyne.io, actually awesome to work with. but holy god it's so ugly, and they've worked themselves into a corner with how they wrote it. theres pr's and discussion ideas to give some users control over something like padding but it'll be a very painful bandaid to pull off and redo. hardcoded vals everywhere.

ive been kind of sitting back and waiting to see if AI was going to help someone who has more inspiration/drive/smarts than me launch something into the spotlight for go gui, but so far the biggest go gui successes still land in the web-technologies stack (wails). i look over at rust and see something like dioxus and i get sad. as far as desktop gui world goes, theres a glaring hole: i actually think aggrid (web tables) is my personal like bare minimum of what im expecting out of a table component. i havent really seen anything that matches it on the native app component front.

yeah perfect, i came in here to say

I'm done making web apps (2026).

seriously desktop apps kinda own i just desktop-app'd a pwa made it do SSO auth at my org and now its just part of the self-serve application download kiosk and we're laughing at all the pain we've endured for so many years writing up proposals and billing to scale up web app infra for internal tooling and stuff.

im kinda enjoying coming back to earth right now with my team and we're just hmmmmmmm'ing a lot of things like this. we've had devops chasing 23498234892% availability with k8s and load balancers and all this stuff and we're now assessing how much of that cruft was completely unnecessary and made everything some amorphous blob of complexity and unpredictable billing & and really gave devops a moat to just say "no" to so many things that came through the pipeline. there's so many things that can just be dragged back to like an actual on premise machine and served up through the internal network. we are... amused at how self-important we made ourselves out to be this past decade.

we're probably like days worth of goofing away from going to buy a few mac minis and plug it into some uninterruptable power supplies and just seeing how un-serious we can get with so much tooling we've built over the years. and for everything else, desktop apps. seriously desktop apps is like free infrastructure if you build it right.

holy shit im right there with you

pretty much none of these big providers are offering the guarantees needed to be taken seriously in workplaces right now. the technology itself isn't offering the deterministic guarantees that should warrant it in the workplace right now. problem is everyone's foot is just on the gas. even if your workplace isnt paying for it, people are just straight up rolling their own personal claude accounts to do work at orgs.

ive been trying to make the case all year that if we're going to let employees do shit with ai, lets try claude. in the past like.. 2-3 weeks all that goodwill has basically evaporated.

local inference needs to take off asap because all of these entities actually suck and i wouldn't trust a single sla with anthropic. they are not acting like a serious company right now, this is a joke.

front end (react etc) feels completely wrong to me. after all this computer science advancement that feels like the spot i point and say yeah thats duct taped together.

i was getting annoyed at the state of shadcn/daisyui/the other six trillion ui patterns that have spawned since the abomination known as materialui and i actually realized liquid glass is the only meaningful step away from that we've seen in quite a long time.

it's still not quite my tempo, looks downright silly in many places, but it has grown on me just a smidge, and i think i'd receive it a little better if it wasn't fundamentally more intensive to render. i think that's a line i can't respect and it feels like a step backwards.

i don't want to wax nostalgic about windows 98 era ui's or the design patterns i see with a lot of qt apps either, like they are imo kind of ugly to me too. but i appreciated the consistency back in the 98 era, and i think a ui that restored 3d beveled looking components, were somewhat expressive but consistent is what i want.

but the world is different now. things like flutter that give people a canvas and let them ground up their entire design language undoubtedly mean consistency can only exist within an entity's control, there likely will never be a unified agreed-upon set of ui standards that span industries and personal computing and different stacks anymore. kinda amusing that improved tooling and frameworks has just resulted in a wild west of user interface design.

ha, i use both. i don't even need to write any platitudes on if linux came to mac, utm or parallels has linux going at near native speed actually happier than it runs on my thinkpad t. i get to enjoy all worlds on my mac and its probably the best multi-target development environment ive ever had, and the hardware is still leagues above literally anything else on the market. dont get me wrong i want more options, im still just waiting for options that deserve to be in this convo. i have zero allegiances to who made it, whoever comes forward with the best hardware gets my money. and my orgs money since i pick the teams hardware.

i can think of absolutely zero publicly traded company boards of this size that would opt for "we're already selling enough devices, we know there's more demand we can't meet, let's not scale up we're really happy with these numbers"

oh god yeah the emulation space is absurd.

i think a lot of attention is rightly attributed to like, i dunno say tiktok/ig "influencing" and how that can send people who gain a lot of notoriety off the deep end. it absolutely has. but so do software projects.

not enough people talk about how software projects also offer up a similar kind of atmosphere: you're suddenly hyperconnected with a whole bunch of humans you don't know and are receiving feedback from people outside of your immediate community. "hackers" for all the interesting ways they've contributed to computer science over the decades also have branches spawned from the original chronically-online, highly-opinionated and sort of antisocial and poorly adjusted sects of civilization. being the face of a project is like pouring rocket fuel on whatever predispositions you might have, and on more than one occasion we've seen people go from occasionally unhinged person to seriously unhinged.

this comes with a lot of bad outcomes for quite a few people, primarily it always has some serious amplification qualities to egos and narcissism. and for genuinely good and kind people who are just trying to share their value/contributions and are suddenly jettisoned into spotlights, we often see them suddenly step back and discontinue work on a project entirely.

we often see these departures and think solely "must be burn out" and don't put much more thought into what that means. but we don't do enough to frame how software projects just elevate people into a position that most people don't do a good job in mentally and socially, and how it deteriorates the pieces of them that make them feel like they're valuable members of a community/tribe. some have luck making their project communities their tribe, but that's obviously a risky step to take. for many who have a successful project, sometimes it starts as the most validation they've ever received and then they don't know how to reconcile with the exponentially-widened audience when negative reception starts pouring in.

daniel micay is just one of like.. many in these sorts of projects i've seen who are simply unfit for the role. for many reasons, i don't think he's a pleasant person at all. i don't have any answers here. i also see this in homebrew scenes for gaming, it's like my least-favorite human petri dish of software development enjoyers. lot of oddball developers in that space and quite a lot of incredibly dramatic fallouts and theatrics that seem to come with the anonymous nature of not tacking your real name / identity to a project, and a consuming audience that has zero idea what goes into development so the negative feedback/demands that come in are in their own way unhinged.

the bulk of their sales is, in fact, hardware sales. there is a strong case to be made that such developments wouldn't land people in squarely linux-as-the-only-OS-on-the-device territory either, but rather dual boot ie those users also participate in the walled garden on the mac os side. we've seen this before in the intel mac era.

It would literally sell more Mac devices I'm not sure what the argument is that OP is making

the absurdity to even entertain this dorks musings.

imagine if tim cook or satya came out and talked about how there needs to be a draft. people would say lol shut up nerd and move on.

some dorkus who heads a company that's just providing over reaching surveillance data to governments so they can do dumb data analytics should have no say in these affairs, and we should promptly discard what they have to say. peter thiel is a sociopath, karp is a dork, these people just want to be known as "the guy with the ideas" and they've crossed deep into the "what are you even saying right now" territory.

tbh we should jettison them into the sun they're kind of a scourge on civilization and clearly lake any real stakes that keep them grounded in the world.

Calculators have never been the medium in which we communicate our human experience and knowledge transfer. Calculators aren't part of the social fabric or culture. Very 2d extrapolation that somehow resulted in an alleged parallel. Language is woven deeply into civilization and our histories & been a part of our species literal survival against the most unforgiving odds/environments. Using what is effectively a ghost writer nukes trust. You cannot ascertain anything about the person behind the blog if it's clear they used AI to write it. And without that there's no way to infer expertise, rule out hallucinations, falsehoods presented as matter of fact, and the whole broad set of things LLM's get wrong because of their limitations as a technology. I have literally nothing to go off of that would prove this person knows what they are talking about. Why would anyone want to consume that?

Would it kill anyone at all to add a preamble that is forthcoming about using AI to write something? A chance to say these are my ideas and I've used claude to help me state it eloquently because <english is not my first language / i dont write well / claude said it better than i ever could> etc ? Not doing that, presenting as more capable/knowing than one probably is, is what destroys trust immediately the moment it's sniffed out that AI was used to write something.

It's irresponsible, a self-nerf, and it's annoying. Venn diagram there is basically a circle. We're all familiar with how vibe coding appears to weaken your ability to write code, like skipping the gym and expecting good muscle density. All I'm saying is people shouldn't be skipping the gym for literally communicating with each other because there's gonna be a lot of times in life where you're not gonna be able to whip out chat jippity to continue a real conversation with another person. Ceding that turf means you're willingly trading your ability to deal with real life scenarios with other human beings for short term gain. It's funny how the universe tends to find balance. Yeah, being well read and expressing ideas well is a skill, it takes work.

> The people who have AI write their articles don’t care if it works or if it’s correct.

I'd build on this: The people who have AI write their articles very likely don't know how their thing works or is correct. High chance they'll stumble when they are expected to speak about whatever it is they are presenting with some authority and demonstration of knowledge. Human to human, not being able to do that = obliterates trust. Places it somewhere near the realm of misinformation, which everyone unilaterally has no interest in consuming.

Good luck to people who want to fluff expertise and present as more-capable for job prospects, the world is shit and I know there's more people who need income than there are jobs that provide for our basic human needs, but this level of AI crutching is just going to bode poorly for those who think this is going to get them where they need to go.

> on Apple Silicon, a WebAssembly module's linear memory can be shared directly with the GPU: no copies, no serialization, no intermediate buffers

enhance

> no copies, no serialization, no intermediate buffers

would it kill people to write their own stuff why are we doing this. out of all the things people immediately cede to AI they cede their human ability to communicate and convey/share ideas. this timeline is bonkers.

jesus thank you, im so wary of any project that isn't going to do this bare minimum. static pages on gh are literally free it feels absurd to post this project to HN without doing that.

yea that is probably the worst part of these techs becoming mainstream services and local-LLM'ing taking off in general: working with them at many points in any architecture no longer feels... deterministic i guess. way too fucking much "heres what i use" but no real best practices yet, just a lot of vague gray area and everyones still in discovery-mode on how to best find some level of determinism or workflow and ways we are benchmarking is seriously a moving target. everyone has their own branded take on what the technology is and their own branded approach on how to use it, and it's probably the murkiest and foggiest time to be in technology fields that i've ever seen :\ seems like weekly/monthly something is outdated, not just the models but the tooling people are parroting as the current best tooling to use. incredibly frustrating. there's simply too much ground to cover for any one person to have any absolute takes on any of it, and because a handful of entities are currently leading the charge draining lakes and trying to compete for every person and every businesses money, there's zero organized frameworks at the top to make some sense of this. they all are banking on their secret sauce, and i _really_ want us all to get away from this. local inference has to succeed imo but goddamn there needs to be some collective working together to rally behind some common strats/frameworks here. im sure there's already countless committees that have been established to try and get in front of this but even that's messy.

i don't know how else to phrase it: this feels like such an unstable landscape, "beta" software/services are running rampant in every industry/company/org/etc and there's absolutely no single resource we can turn to to help stay ahead of & plan for the rapidly-evolving landscape. every, and i mean every company, is incredibly irresponsible for using this stuff. including my own. once again though, cat's already out of the bag. now we fight for our lives trying to contain it and ensure things are well understood and implemented properly...which seems to be the steepest uphill battle of my life

yup same just tried it myself which an email I wrote.

like llms are using our language here so there's gonna be patterns we use that they also use.

i dont think we're ever going to get to a place where we have a "yes/no this was written by AI" kind of tool. i do be worrying what this might do to the fabric of society but there's no puttin this damn cat back in the bag so i guess we'll find out

im hoping and praying that local inference finds it's way to some sort of baseline that we're all depending on claude for here. that would help shape hardware designs on personal devices probably something in the direction of what apple has been doing.

ive had to like tune out of the LLM scene because it's just a huge mess. It feels impossible to actually get benchmarks, it's insanely hard to get a grasp on what everyone is talking about, bots galore championing whatever model, it's just way too much craze and hype and misinformation. what I do know is we can't keep draining lakes with datacenters here and letting companies that are willing to heel turn on a whim basically control the output of all companies. that's not going to work, we collectively have to find a way to make local inference the path forward.

everyone's foot is on the gas. all orgs, all execs, all peoples working jobs. there's no putting this stuff down, and it's exhausting but we have to be using claude like _right now_. pretty much every company is already completely locked in to openai/gemini/claude and for some unfortunate ones copilot. this was a utility vendor lock in capture that happened faster than anything ive ever seen in my life & I already am desperate for a way to get my org out of this.

> 4.7 is going to replace both 4.5 and 4.6

as in 4.5 is no longer going to be avail? F.

ive also been sticking with 4.5 that sucks

is it 5 mins between constant prompting/work or 5 mins as in if i step away from the comp for 5 mins and comp back and prompt again im not subject to reinit?

if it's the latter that's crazy. i dont even know what to do there, compactions already feel like a memory wipe

when you say "same prompt" are you saying its similar prompt and something in the middle determines that "this is basically the same question" or is it looking for someone who for whatever reason prompted, then copied and pasted that prompt and prompted it again word for word?

at least for our scope of work (data, interfacing with data, building things to extract data quickly and dump to warehouse, resuming) claude is performing night and day better than codex. we're still continuing tinkering with codex here to see if we're happy with it but it's taking a lot more human-in-the-loop to keep it from going down the wrong path and we're finding that we're constantly prompt-nudging it to the end result. for the most part after ~3 days we're not super happy with it. kinda feels like claude did last year idk. it's worth checking out and seeing if it's succeeding at the stuff you want it to do.

ran into this literally yesterday. so im gonna assume yes.

noticing sharp uptick in "i switched to codex" replies lately. a "codex for everything" post flocking the front page on the day of the opus 4.7 release

me and coworker just gave codex a 3 day pilot and it was not even close to the accuracy and ability to complete & problem solve through what we've been using claude for.

are we being spammed? great. annoying. i clicked into this to read the differences and initial experiences about claude 4.7.

anyone who is writing "im using codex now" clearly isn't here to share their experiences with opus 4.7. if codex is good, then the merits will organically speak for themselves. as of 2026-04-16 codex still is not the tool that is replacing our claude-toolbelt. i have no dog in this fight and am happy to pivot whenever a new darkhorse rises up, but codex in my scope of work isn't that darkhorse & every single "codex just gets it done" post needs to be taken with a massive brick of salt at this point. you codex guys did that to yourselves and might preemptively shoot yourselves in the foot here if you can't figure out a way to actually put codex through the ringer and talk about it in its own dedicated thread, these types of posts are not it.