HNHacker News
TopNewBestAskShowJobs

BikiniPrince

355 karma · joined January 4, 2021

submissionscomments
BikiniPrince··on OpenAI CLI
Curl with token usage so it’s better.
BikiniPrince··on OpenAI CLI
It’s all greenfield and I’m not surprised to see deprecation. Eventually tooling will distill into what works.
BikiniPrince··on The Other Epidemic: Trying to get off benzodiazepines
This also just reminds me of the sensible things to ask your doctor when they try to prescribe a drug. Can I simply stop taking this drug? For two people I know in the last year this would have been a nice question to ask.
BikiniPrince··on Ofcom concedes defeat in 4chan case
How many of those organizations had business within Ofcoms jurisdiction? No one operating outside of their legal jurisdiction should have complied.
BikiniPrince··on Tesla Roadster
Bo and Luke Duke would disagree.
BikiniPrince··on Most data centers refusing to say how much water, electricity they use
I have yet to see the standardization in that claim. Are there some reliable papers on this topic?
BikiniPrince··on Most data centers refusing to say how much water, electricity they use
Industry uses resources and they pay for those resources at significant cost. It’s not a surprise when the pipes are enabled.
BikiniPrince··on Can AI Shopping Agents Be Trusted?
The poor are not wasting money on agents. They will just go to the store and buy a coat.
BikiniPrince··on Claude Cowork and chat are now one Claude
I solved this with task management and got work trees.

The downside of course is branching in got, but I usually don’t go of course more then a handful of tasks.

I had to engineer my own ticket management to keep opus on target. It’s been great for managing work, history, audit trails and commits are tagged with the task id.

I implemented subtasks to deal with the way Claude likes to stage its own objectives.

Then I made enforcement logic in the task manager so tasks can’t be closed out until reviewers have consensus on the same sha.

The adhd that is Anthropic demanded I build it and now I’m knocking out issues faster than Batman.

BikiniPrince··on GPT-6 Astra, looped transformers, and hidden reasoning
I'm still working through my first few days, but I've had to deal with Opus ADHD for a while. I built a task management system which is closer to old school remedy with reviewers. The stylistic guidelines on task creation have a seven part problem statement, goal, success, ancillary data and such. By framing the task diligently it does keep the work on target. The review logic is basked into the task management software so the agent can't declare done. On open ended issues it can still wander. It's been remarkable to drive down issues over these last few weeks. I was annoyed I had to stop for 3 days and build management infrastructure, but it's paid for itself.
BikiniPrince··on Claude, change the “Add to Cart” button to blue
Listen Pal, this is load bearing. If you know what is good for you then you will stop asking questions. —Claude
BikiniPrince··on Which tools do Claude, Codex and Cursor choose? We measured 17k runs to find out
The framework recommendations are always funny, but the worst is database layout. I made the mistake of assuming it has some reasonable sense.
BikiniPrince··on We found a division by zero bug in FFmpeg with a vibecoded fuzzer
That hasn’t been that bad. My real issue has been the time sink involved in following along with the maintainer and jumper through their hoops. Even after I demonstrate a flaw and a potential fix. My schedule is just so busy I need to pencil in time to deal with them.
BikiniPrince··on Saving 100 terabytes of memory by optimizing 1.1.1.1's DNS cache
Funny thing about cloudflare. I have a dns warming script that uses their top 1k or 10k addresses. Then when my master starts up it warms the entire cache. Everything else uses memcache so the cluster is nice and toasty. As far as I can tell no one else releases domain statistics like them.
BikiniPrince··on We found a division by zero bug in FFmpeg with a vibecoded fuzzer
Funny thing, I know I'm brushing up against something in gStreamer developer, but Fable flips out. I have only a loose idea where the issue might be lurking.

Next week, I'll apply for the cyber and I suspect I'll find something similar.

Right now, it's just annoying and thanks the OpenAI cyber was much easier to get access to.

BikiniPrince··on Grand jury declines to indict Ohio man charged with destroying Flock camera
At least three pounds of copper and no jury will convict you!
BikiniPrince··on New Orleans will use AI to answer 911 calls instead of a human
911 isnt the bottle neck unless we start rolling out robocops.
BikiniPrince··on New Orleans is testing Carbyne’s AI-powered Emergency Call Triage software
I can’t even get through the banks automated live agent in a non-emergency. This is just going to be a disaster. I still have memories of McDonalds trying this and the insanity the order became was hilarious.
BikiniPrince··on Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
I use detailed project files. It has data regarding the project and subtasks as well as task status. It doesn’t depend on agent context and it’s managed to keep the agent on track. Feature creep with the new models is a very real issue. Capturing principles and how to reconcile tasks helps too. Even today it brought up a source of truth issue it had detected. There were multiple authorities born out of a patch and it used that principle to highlight and resolve the problem.
BikiniPrince··on Beating GPT-5.6 Sol on retrieval with 100x cheaper open models
You can register models with mcp. I think it’s an expensive solution, but it is available in the framework. I use a light weight bus protocol that lets agents interact and pass short messages with pointers. It’s very efficient.
BikiniPrince··on AI bet goes awry: Oracle fires 21,000 employees
They just deleted some TPM positions.
BikiniPrince··on Judge approves $1.5B Anthropic settlement for pirated books used to train Claude
How is this ruled as piracy then? I am confused.
BikiniPrince··on The classifiers Anthropic puts in front of Fable are too zealous
I can’t even use it to fix the bugs Opus introduced. I’ve considered ripping out auth until fable is behind the paywall. I’ve been very careful in my queries and broken everything down to careful segments. Even the memory can get security verbs poisoning further requests.
BikiniPrince··on Microsoft fire idTech team at Id software
Id made games to demo their engine. No one is going to buy an engine without any games. They don’t even sell idTech anymore. It’s used for their games which are not making any money. No game sales doesn’t support the reasoning they should keep the engine around.
BikiniPrince··on Microsoft fire idTech team at Id software
It’s a little simpler than that. The games that use this engine have poor sales and no one is even buying idTech. There isn’t any reason to keep them around when Microsoft is losing 64 cents on every dollar. They chopped every unprofitable studio and cast several to their own budgets. Presumably they are going to sell off the mediocre studios and IP.
BikiniPrince··on OpenWrt One – Open Hardware Router
Gl.Inet ships with their openwrt version. I have the last version and it can be flashed to vanilla openwrt or one a high speed branch. It’s been good and fast. I don’t need wifi 7 yet so I have time.
BikiniPrince··on Why I'm Forced to Say Farewell: Google Management Has Lost Its Moral Compass
Also his complaints about morale compass failure are largely activism goals. Hard to make money when you waste it.

I tell employers I’m clearly a mercenary and I am only here for the money. I do great work, but I’ve been compensated well.

BikiniPrince··on GLM 5.2 beats Claude in our benchmarks
This is a joke right? I wouldn't install this in a sandbox.
BikiniPrince··on GLM 5.2 beats Claude in our benchmarks
You have to forgive the GLM bot. It's not very good.
BikiniPrince··on Ask HN: Is "no source code was copied" still a sufficient copyright defense?
I looked at those screen shots. The language is similar but it’s not verbatim. The is itself is just the usage of the same framework. Business logic can’t be copyrighted. Is it too close? I agree. Does it cross the legal test. I wouldn’t waste my money on a court battle.
Page 1 of 6Next →