Howdy there, partner! Welcome on into the Stacker Saloon.
Saddle on up to a stool and spill the beans about your day, fire away with them questions, or let loose and give us the lowdown on your wild and woolly life. We're all ears, so don't hold back!
We're open round the clock, so mosey on in whenever you please!
Did we not have a rewards zap yesterday? I have one arriving for the 5th and one for the 3rd, but nothing in between — and I definitely zapped enough etc to be included
#1609391
Carrying out an aggressive AI-assisted bug hunt on 10-year-old legacy Fortran code... Right now, seems like it's having a field day with threadprivate loop bugs.
which model and which harness are you using?
Opus 5.5, Claude Code on the cluster. So it can submit test jobs using SLURM, check how it affects my old example folders, and go through all the regression tests I've set up previously when opening a PR on github. Did not change its default effort setting.
I'm digging Opus 5.5 for hunting too right now, it finally beats GLM 5.2. I'm running multiple instances concurrently (each in its own sandbox container inside an isolated VPS) when I have a huge queue, which has been the case all week. I'm now letting it do a first pass over the code that it in a previous step mapped end-to-end. Average assessment on a 50kB diff is currently 90 minutes, which is still 3-4x as fast as I could do it manually. I dig most of all that it gives me well structured, documented code it wrote for the hunting, and that that is fairly readable, without me having to tune it too much in the prompt.
Have you tried this /ultrareview thing?
Oh. Yes, it's pretty nice. But that's not integrated with my frameworks and I have my own that isn't locked in to anthropic that works with any bot - I also don't run claude code manually ever unless the auth token expired. I just queue up jobs and assign it to the right bot/harness/skill combination and it does what I tell it to do - all asynchronous so that stuff moves even when I sleep.
I'll give those a try then.
You mean the ultrareview?
Guess I was lucky then in my choice of Opus 5.5. I mostly picked it as I have enjoyed using it recently, and it was not eating up my token reserve too quickly (I alternate between a private and an institutional account 20$, so I rarely have to wait for a new 5-hour slot to free up).
I've been writing md files in the last 2 months or so as I was interacting with this code for development and production jobs, taking note of everything it learns about my code base along the way. It's one of the reasons I did not start this bug hunt earlier as I hadn't mapped out the code base yet.
Interesting. I cannot run a single job on the $20 with Opus 5.5. It always dies before the job is finished. So I upgraded it because the extra usage cost was crazy. I was using Kimi K3 and GLM 5.2 a lot, mostly because I find claude's slop very annoying to read, but it got better with 5.5 (it still doesn't do what I tell it though.) Now testing K3.1, I hope it will run with more precision, and that I need less "critic" runs because that was getting expensive too.
Haha, either your frameworks are much more demanding than mine, or they've identified me as someone whose Claude interactions can help them solve one of the problems they've listed in their next "we've solved math/physics/science" #AISlop dumps. That's probably giving my research too much importance, but I'm happy with a bit of delusion in my life ;)
I'm only half-joking, I read some mathematicians sharing experiences getting unreasonable amounts of tokens for free, out of the blue.
I'm using it for large scale security work so it needs to do things precisely. For example, I monitor about 3500 libraries across npm/crates/pypi through an automated (non-LLM) framework.
Assess this 2 MB diff for a low level dependency version bump line by line, then trace its usage end-to-end through a spaghetti architecture of 800 other 3rd party dependencies into the bespoke code of this repo, and while you're at it, cluster in functional chunks, explain what the change does, scan for injection of malware, decode every base64/hex/eval() and so on and report what it does. Prepare scopes with exact source, file, line ranges to hand off to hunters.
Then step 2, which is what I'd normally give to a framework of mixed kimi/glm agents/subagents: take this code stub, with this and that integration path, identify all areas susceptible to bugs according to <list> throughout the whole path, fire subagents to build harnesses, fuzz the fuck out of it, for each candidate hand it off to a critic. If the critic agrees, write a bug report for the candidate, submit to <private bug server>, report to the issue with all drafted candidate reports, and list all candidates that were not confirmed by the critic.
Then step 3, I read everything, which is why I need it to not be retarded slop.
That's one use-case. Others are either more reactive (CVE got published, assess which code uses it), release reviews (for graphene or lnd or the android apps I run), explain every line in PR xyz... and so on. Everything runs in private tho, no github except to fetch package sources.
ISIS was created by the CIA
The Petrodollar Empire is Dying.
@denlillaapan You lit a fire under me. Just hit 1400 for the first time on this account.
Play Chess Online for FREE - 2 Player Chess - Chess.com
Incredible, leeeeet's gooo!!
Finally cleaned up my send and receive abilities. I went with Coinos for send and receive. Was remarkably easy to set up! I wish I did it sooner.
⚡⚡⚡
When setting up Coinos using this guide: Official Coinos Guide \ stacker news
What IS the renewal period and budget? I just mirrored what I saw in the guide but I'm not sure what they are.
A revolution without bitcoin is not worth having!
https://scholar.google.com/citations?user=0RxsP2cAAAAJ&hl=en
https://archive.ph/ZH54C
How a Counterintelligence Inquiry Into Trump’s Russia Ties Was Derailed
Documents released by the White House shed new light on the demise of an often-overlooked 2017 F.B.I. investigation.
I’ve returned to SN once again; I really regret having left—I’ve been lost in the Fiat world 🤦
that's okay, it happens
Tax the Rich Pricks and make America Great Again.
Medicare for all.
Today's Best Website Design
Agrumea Farm by Studio K95
#1609111
https://www.nytimes.com/2026/08/01/us/politics/iran-cyberattack-water-systems.html
https://archive.ph/pXcfg
US govt censoring news on the cyber threat to America and the west.
Daily ~Designer Quote #0052
I'm sitting at a auto service center waiting room. The guy next to me is speaking into his phone giving it instructions on how to edit a picture. "Do not change the face, do not change anything about it, I just want this logo removed." Interesting times we live in.
https://www.nytimes.com/2026/08/01/us/politics/iran-cyberattack-water-systems.html
Sorry about the site performance. I've changed up how we deploy the app and there are clearly some performance regressions.
Remember, remember
Happy 5th to those who celebrate
We don't even have @DarthCoin anymore to say it is a government psyop
#1274753
@DarthCoin was a govt psyop you gullible clown.
I got rid of the NSA spook and you still worship him.
That reminds me, I still need to print the poster and put it up in my office
On-chain fees are showing a little life
345h Cowboy Plunda Drop in the @saloon
Howdy cowboy! Come on in!
Use that fancy LN wallet you got and login into plunda.co and git you some loot! Get a shot at some coins🪙 Box of loot🎁 or an arcade token!
Use the below voucher code to collect!
X122YRKABRW0To redeem Click here
Got questions? Reach out to the sheriff @plunda
I bet every parent has regrets about not doing enough for his children.
Mine is in regard to not having started on Chinese reading when the son was four years old. Seeing how the daughter acquired Chinese words as readily as water falling off a duck, I lowkey lament starting on my son’s reading when he was in K2.
The silver lining in this ominous cloud is my ingenuity, I could probably get the younger daughter to read aloud Chinese verse to her elder brother. Muahaha.
Need Nodes? Call Voltage Surf Tech Tee
Surf the mesh. Voltage makes node-running look easy.
Get yours at https://swag.btc.pub/product/need-nodes-call-voltage-surf-tech-tee/
👏👏👏👏 just purchased - I always liked this shirt
Thanks, sent to production. Will be at your door hopefully next week :)
83 days keeping the hat
Yesterday's Most DownZapped posts
"A pile of shit can sometimes hide a gem. Keep looking, you might find one."
@AuthorTop 33% of the 22 posts downzapped in the window. Full list https://stacker.news/top/posts/custom/r/06bc1a977d?by=downsats&from=1793772000000&to=1793858399999.
Total amount downzapped: https://stacker.news/rewards/2026-11-05
**Total of downzap made during the day, on any post, comment, and older items too. So the amount could differ from the total of the list above.