Hacker Newsnew | past | comments | ask | show | jobs | submit | vladgur's commentslogin

Imm overwhelmed with a variety of SDD tools out there.

Github spec kit, spec-kitty, symphony, GSD, this.

How do people decide on the framework other than try them all.

p.s. found this mind-boggling list of them all https://github.com/cameronsjo/spec-compare


I think any add-on SDD is diluting the context and should be using as much as possible anything that is built-in and not external skill. When Claude (or any other lm) begins to ignore the rules, ask it and it will tell you that having too much in context will make it go bad faster.

I looked at most of those, including kiro and tessl. Was early user of GSD when it was suitable for mid+ size projects. Over time GSD grown into beast which is suitable for huge + size projects only producing gigantic specs and burning too many tokens for most of the tasks. So I decided to created my own, with set of steps I need and specs I want.

After few presentations of sddw to different companies, most important conclusion was that the ssd plugin should be customizable. It should fit the typical size of tasks/features you are working on, specs should fit your requirements, set of steps can be different.

So I created claude code workflow (ccw) which allows to compile custom version of workflow on top of sdd approach: https://github.com/sermakarevich/ccw

After making few presentations of sddw to different companies,


In unrelated news

"More than 600 University of California faculty members, led by mathematicians at UC Berkeley, are calling on the system to reinstate standardized testing requirements for science, technology, engineering and mathematics applicants, saying that six years of test-free admissions has not reliably assessed readiness and professors are often teaching middle school math to incoming students."

https://archive.ph/18spS


Hard to find the actual letter: https://ucstudentsuccess.org

Who even makes the decision to drop having a standard bar to verify students?

And what possible benefit would that have?


The book SAT Wars has arguments for and against and the striking thing for me was that some in admissions believe in a concept called crafting a class: the applicants are input into the admissions officer’s artisanal contribution to producing a class that they believe would be good for the university to have.

The idea of a standard bar and so on does sound like it would interfere with such a process.

I always did find it interesting that US notions of anti-racism required treating individuals not as individuals but as racial representatives. It’s a local quirk of the culture of the land, I suppose, that one’s primary identification here is one’s skin colour.


America's vapid fixation with race is ridiculous especially since it uses race as a proxy for social stratum when it could just be addressing class issues directly instead. If only there were some history of forms that parents fill out every year showing their income to the government that is more-or-less vetted to some degree—too bad we don't have such a thing that students could use to prove social stratum! Plus, what the hell is race anyway? An unethical tip one could give to university applicants would be to claim membership to the most beneficial group because it's not like university admissions has any way of proving your "race". Construct any fabricated story that'll get the most approval and maximize your chances of getting into a top university.

Unfortunately, the fixation with race in America doesn't start nor stop at college admissions. College admissions is probably the last place where it tilts in the direction of certain minority groups.

I agree that we should just stop using race everywhere and we should crack down on it -- but I think college wouldn't be where my energy would be... actually the military is where I'd start. And oddly it's the place where race based affirmative action is still permitted (military academies - where it benefits minorities) and in its halls (where I've heard that it has a strong white supremacist bent). The reason is because what is happening in colleges is more reactionary -- fix the catalyst and the arguments for the reaction largely go away.


The very real downside is if you just provide equal opportunity then you would still end up with an all white/East Asian/Indian class. You can argue that this is fair and meritocratic and you would be right but I believe there are a lot of people that see value in affirmative action that makes classrooms look more like the racial distribution of the country and provides an easy step up for traditionally poor/downtrodden communities to improve themselves. Affirmative action isn’t only an American thing btw, it’s in China, South Korea, India etc. as well.

Why else does anyone in California get rid of anything? Because it’s racist.

You should probably take a look at the demographics of the top scores of the standardized tests like the SAT. You're not going to find the race you think at the top.

Do you think I wouldn’t know?

Pray tell which race do you think I’m going to expect to find?

Because let me tell you, the demographics are pretty much exactly what I expected. And my response to that is…so what?

If anything you’re telling on yourself with your statement.


Rather than have me guess about what you know, would you care to explain what you meant by your original comment then? What exactly were you referring to as "racist"?

I read his comment as tongue-in-cheek.

Why was SAT gotten rid off - testing is racist.

Why is 6-8th grade accelerated math pathway gotten rid off - math is racist

https://edsource.org/2021/california-math-guidance-sparks-ne...


See: when they banned guns because of the black panthers.

The decision wasn't specifically to drop a standard bar. It was to drop the existing bars because they have become heavily gamed and are far more reliable indicators of your family's resources than your ability or likelihood of success. That was the equity argument.

Unfortunately, the lost signal wasn't replaced with anything. (I don't know what could replace it. It's an incredibly hard problem. )


Easily gamed? Sure, education is pay to win on some level but we're talking basic prerequisites here. If the objection is that disadvantaged would-be students are being filtered out then start an outreach program to help them prep or something.

I thought for most universities it was because some schools didn't organise the tests and others did during COVID.

More leeway in who you accept (for money and/or clout).

macOS mail app is a special type of terrible especially if you deal with multiple email accounts. Every os upgrade causes various bugs such as search index all of the sudden not working and you have to reset and reimport all your mailboxes

I agree. Mail.app is one of the buggiest pieces of software I have ever used. It has some nice features as well, especially the editor. But some of the bugs I have experienced were catastrophic, such as silently failing exports that appeared to have completed successfully (this was recently fixed after years).

I've used Mail.app since 2004 and have not had any of those problems except searching using Spotlight have occasionally been broken over the years, but never searching within the app.

And I've had both multiple accounts various servers both private and work. And dozens of work-related role aliases which Mail.app correctly always used when replying. No problems there. Neither I have had to rebuild sqlite mail folder db, but did have some quirks first when work emails were transferred to Office365 which wanted to rename folders etc. nuisance, 2FA worked also worked fine since IIRC Mojave. I've had some addons MacGPG, sorting and maintenance scripts too. MacGPG does need some attention when upgrading though besides paying for subscription it moved time ago.

I've used also Thunderbird, mostly with linux. And used and tested whole lot of various clients since Elm was a thing -80's, then Pine, mutt etc.

The macOS Mail.app is fast reliable in my opinion, but sure there are things in its UX it could be yet improved. But still it's been long time among best and never broken or let me down over 20 years, both work and private use.


Which models do folks use for openclaw nowadays


I've been using DeepSeek Flash to replace Sonnet once the subscription stopped working. Haven't really noticed a difference, although I don't usually have it doing anything very complicated.


From my failed and expensive affair with GPU mining 5 years ago, You can get a great heat dissipation outcome by using an open case with a lot of directed fans at the expense of a bit of dust and lots of noise


I dont like David Sacks opinions on anything geopolitical, but respect his opinions on tech and identity politics.

That said, this article is by a political writer and even though its on the Verge, its a political opinion piece(ie the centerpiece of it that he was PUSHED OUT -- could use some evidence)

I dont think that belongs to HN.


That window seat with the 14” laptop seems extremely claustrophobic.

That’s the real limitation on an economy flight - space rather than power or the internet… at least it would be for me.

The only times I was able to get my laptop out and do some productive work was when I either was sitting in premium economy isle seat with room to spare or when there was an empty seat next to me


I'd probably choose the window seat myself, because while it is cramped, it is predictably so. When I sit in an aisle seat, it's not as cramped but I regularly get shoulder checked by passing people or beverage carts.

What really makes me nervous if I'm in an economy seat is the seat in front of me. Depending on how the seat is designed, if the person suddenly reclines (or hell, just flexes the seat a bunch while moving around), it can come pretty close to pinching the laptop screen. That would be bad news.


That was the first thing I thought of when I saw the image. That's a very expensive computer that you risk destroying when the 300lb guy in front of you decides to lean back.

The ergonomics of using a laptop on an economy-class tray table are not worth it. You're sitting there like a T-rex trying to make your arms as small as possible to tap on the keys. And the vertical viewing angle to your screen sometimes prevents you from even seeing anything. I wouldn't even bring my laptop out during a flight.


>The ergonomics of using a laptop on an economy-class tray table are not worth it. You're sitting there like a T-rex

The trick I've found is to pack a bluetooth keyboard. If you put your laptop on the tray table, you can put the bluetooth keyboard on your legs _under_ the tray table and have your arms fully and comfortably extended. This works especially well if you're a vim/emacs/other keyboard driven editor user as you very rarely need to reach up to poke the trackpad .


You just learn how to type with your toes. It is an easy skill to master and then comes handy when you drive, or sit at important meetings (you can just keep coding away) and noone's the wiser.


In the image it's on his lap, not the tray table. I agree, using the tray is not worth it. The ideal is a tray that folds in half so I can use that to hold a drink and keep the machine on my lap.

The tradeoff of poor comfort is insane productivity, for me anyway. Being restricted in place, no wifi, inconvenient toilet breaks, not in control of meal times, all means I get a lot of work done


Obese people (250lb+) shouldn't even be allowed in Economy.


Maybe.

On the other hand, in economy on some planes I just literally don't fit in a forward direction because of femur length and cycling muscles, I don't fit in a sideways direction either because of broad shoulders and arm muscles, and I don't comfortably fit vertically on some planes with fixed-position headrests which push into the middle of my shoulder blades and have me hunched the whole flight.

I'm also not _that_ big. I'm 6'2" and have lived my life moderately actively. That's it. I'm biased, but I believe economy should be designed so that I can fit too.

If you agree with that premise, that'd leave plenty of space for most 250lb people too, and there'd be no reason to exclude them.


Man, I hate being rude because I myself weighed 230lbs once upon a time, I get it. I just dealt with a 200lb+ man who spread his legs past the arm rests. Pissed me off the whole flight because I had to contort my body in my own seat so he wasn't spilling into me.


You didn’t have to, but possibly that was preferable to confrontation.


Sweet, free upgrades!

Edit to be slightly less obtuse: surely you're not implying that a common carrier be allowed to discriminate based on facts about a passenger's body without making reasonable accommodations. Surely you're not implying that obese people not be allowed to fly at all. Surely you're not suggesting that fat people should just remove themselves from society so you don't have to deal with them.

Therefore, obese people should get free upgrades to economy plus or better. Thanks for the idea!


Free upgrades sound reasonable to me. Especially if obesity becomes less common via GLP-1s.


I'll imply those things. If you don't fit in the seat, you should have to buy two seats is a not very controversial opinion on the internet IMO. I think that opinion basically violates all of your "surely"s already.

Where do you draw the line? A 250lb person probably mostly fits in their seat still, but at some point a person is just physically going to take up two seats. Do you really think the airline should be responsible for flying them in business class (premium economy doesn't give you more width on most/all airlines)? Does it matter if their weight is due to a medical condition or just laziness? What if they're so big that even a first class seat won't contain them?


The issue is for the airline to solve, since they are the ones trying to make seats comically small.

Also, you have to include other attributes. E.g. Not my problem that you have freakishly long legs, if you have to prevent me reclining then maybe you should have to pay for premium economy. And what if you are broad shouldered? Same deal, not my problem, you have to stay inside the boundaries of your own seat.

I would rather we used regulation to make economy seats a bit larger. Call it a safety issue, since it is.


The downvote the upvote ratios in this thread imply that significant amounts of HN are land whales.


How about having a law that ban super tight economic seat?


What are you, a communist? /s


Packing people into tiny spaces like sardines should be illegal.


I have a 16" M1 Max that I only got because it was $1500 cheaper than MSRP, and it sucks on planes. I have really long arms and I can barely get it out of my bag without elbowing my neighbor.

A few years ago I saw some very interesting custom ergonomic setups optimized for traveling + flying.

One person with a thinkpad is able to get the monitor to be 180 degrees flat w/ the keyboard, and can hang it off the seat. He also brings a split ergo keyboard with a lap mount.

Another person did something similar with a M1 laptop, but needs an Ipad to act as the external monitor (laptop stays in bag) with a built and designed from scratch split ergo keyboard.


I got some Xreal glasses and it's made flights so much more enjoyable. I can watch movies or work on something lying back, and the "screen" looks massive.


I’ve been so tempted but some of the reviews say it’s not good for reading code. What’s been your experience? What is the effective resolution of the screen you get? Is it sharp enough for coding?


Currently working on an Amtrak with XReal One Pro glasses and a ThinkPad bluetooth keyboard from my Macbook Pro that is folded up in the seat pocket.

They are "OK enough" that it will be a matter of taste if they are acceptable or not at this point for you to use.

For coding they work fine for me, terminal tools work particularly well as I can bump the font size up. IDEs and web browsing aren't bad either, it's about the equivalent of a single 1080p screen. They are nicer than hunching over a laptop for travel use but I still prefer a proper monitor when available.

The optics are a generation or two from being where they need to be to market these as productivity devices, but if you like being an early adopter with all the quirks that come with it, they're fun.


It's a definite "it depends". The resolution is fine, but I think it's more about the specific pair of glasses you get? I got the same model three times (long story), and the first two were fine, the third has some blurring in the middle of the right eye.

It's also uncomfortable to look at the very bottom of the screen (which is where all the chat text boxes are), so I usually resize all my windows to be a bit smaller. With that, it's very good (and you can always just increase the font size).

I would like glasses with smaller fov, so I didn't have to look around so much, but that's probably just me, since everyone else likes them larger.


Don’t listen to anyone saying it is fine for reading or writing extensively with the xReal. I have one and it is PITA to do that over a long period. You better just stick with watching videos or playing games with it.


They're like reading a projector. It's not very good, but it's better than awkwardly staring at the computer screen.


That's a 16" (from the size of the speaker grille on each side of the keyboard), so even more claustrophobic.


This is getting very close to fit a single 3090 with 24gb VRAM :)


Yup! Smaller quants will fit within 24GB but they might sacrifice context length.

I’m excited to try out the MLX version to see if 32GB of memory from a Pro M-series Mac can get some acceptable tok/s with longer context. HuggingFace has uploaded some MLX versions already.


I have an Mini M4 Pro with 64GB of 273GB/s memory bandwidth and it's borderline with 3.5-27B. I assume this one is the same. I don't know a ton, but I think it's the memory bandwidth that limits it. It's similar on a DGX Spark I have access to (almost the same memory bandwidth).

It's been a while since I tried it, but I think I was getting around 12-15 tokens per second an that feels slow when you're used to the big commercial models. Whenever I actually want to do stuff with the open source models, I always find myself falling back to OpenRouter.

I tried Intel/Qwen3.6-35B-A3B-int4-AutoRound on a DGX Spark a couple days ago and that felt usable speed wise. I don't know about quality, but that's like running a 3B parameter model. 27B is a lot slower.

I'm not sure if I "get" the local AI stuff everyone is selling. I love the idea of it, but what's the point of 128GB of shared memory on a DGX Spark if I can only run a 20-30GB model before the slow speed makes it unusable?


There are a number of DGX benchmarks for these recent gemma-4 / qwen-3.6 models on the nvidia forum, ex: https://forums.developer.nvidia.com/t/qwen-qwen3-6-35b-a3b-a...


Tbf the Sparks usefulness isn’t for inference IMO. Its memory bandwidth is too low for that.

But on the other hand, running Qwen 3.5 122B A10B locally on it using ~110GB of memory and getting 50tk/s generation and quite excellent prefill… I couldn’t do that on many other machines at this price point

For me this has been awesome to learn CUDA on, fine tuning models (until I get it close to what I want then it’s off to H100 or something clusters) and a bit of inference on the side


32GB RAM on mac also need to host OS, software, and other stuff. There may not even be 24GB VRAM left for the model.


At 4-bit quantization it should already fit quite nicely.


Unfortunately not with a reasonable context length.


I've got 139k context with the UD-Q4_K_XL on a 4090, q8_0 ctk/v. Could probably squeeze a little more but that's enough for me for the moment.


Hey, buddy! Can I bum a command line arg list off ya?


The model uses Gated DeltaNet and Gated Attention so the memory usage of the KV cache is very low, even at BF16 precision.


It really depends on what you think a reasonable context length is, but I can get 50k-60k on a 4090.


I used to run qwen3.5 27b Q4_k_M on a single 3090 with these llama-server flags successfully: `-ngl 99 -c 262144 -fa on --cache-type-k q4_0 --cache-type-v q4_0`


With CPU offloading of e.g. 25% on that hardware it is still fast enough for a lot of things.


We do - gave me a few second warning of a 4-point one a month or so ago

https://apps.apple.com/us/app/myshake-earthquake-alerts/id14...


Curious which models are you able to run and how many 3090s do they require at scale?


4 3090s with nvlinks on each pair. Super fast inference on Moe models around 20-36b


> Super fast inference

How fast is "super fast" exactly, and with what runtime+model+quant specifically? Curious to see how how 4x 3090s compare to 1x Pro 6000, could probably put together 4x 3090s for a fraction of the cost compared to the Pro 6000, but the times I've seen the tok/s in/out for multiple GPUs my heart always drops a little.


I haven't benchmarked against a pro 6000, it's more that i have 4 3090s and i don't have a pro 6000.


Yes, that's why I'm asking you what exactly 4 3090s get in prompt-processing and generation, sorry if I was unclear.


Maxes out around 4K tok/s output. Each pair of 3090s has its own instance of the model with parallelism across the nvlink bridge. Though nvlink is only 2x over pcie5


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: