HNHacker News
TopNewBestAskShowJobs

361994752

111 karma · joined July 13, 2017

submissionscomments
361994752··on Show HN: Open-source model routing for coding agents at Astra-level performance
Ofc :) Asking this because we have copilot at work (assuming it is quite common for enterprise)
361994752··on Show HN: Open-source model routing for coding agents at Astra-level performance
Sounds very interesting. Do you have plan to support gh copilot as model provider?
361994752··on ASML currently sells no chipmaking machines in Europe, executive says
then just hire them in asia.. and stick to globalization...?
361994752··on Show HN: Jev Plays Pokémon Red
watched it stuck at rocket hideout for 10 mins.... let me check 1hr later to see if it can find a way out
361994752··on Claude discovers a novel enzyme system with CRISPR-like repeats
and they can explain it in whichever why they like
361994752··on Hister: A private search engine for the pages you visit and the files you keep
There should be no real vendor lock in in my opinion. You can ask the same question with pi + qwen (or any harness + good enough model) with internet access and it will work. Chatgpt is just one option came in handy.
361994752··on Hister: A private search engine for the pages you visit and the files you keep
No I don't share anything with chatgpt. But I do have a $20 subscription, if it matters. I feel It's just capable enough to find what I want from my usually vague and inaccurate description.
361994752··on Hister: A private search engine for the pages you visit and the files you keep
I had the same problem for a very long time but it is largely solved now. I started to simply ask chatgpt "hey I read something about x, y month ago but can't find it now". There is a surprisingly high chance chatbot can just give the exact answer back to me, usually with extra interesting reading materials as a plus.
361994752··on Training a 4B model to produce 81% faster query plans than Postgres
Good and bad plans can have orders of magnitude performance difference. The bad one can easily do enough damage cutting the performance in half before it is canceled.
361994752··on How much oil-market buffer is left?
Since oil companies will make good money from the price hike and exports, I guess they’ll lobby against an export ban?
361994752··on DeepSeek v4.1 flash runs 23 seconds/token on a 2020 16gb M1 Mac Mini
I fell into the trap (again)
361994752··on FDA clears blood test to aid evaluation for Alzheimer's disease
I lost my grandma because of this. She was taken care of by my uncle and my father, and deep in my heart, part of me blames them for not doing their best. At the same time, I know they did way more than I ever could have done. It’s just so hard to take care of someone like that.
361994752··on The road to ACID transactions in Cassandra 6
Why is java bad here...? Because of GC?
361994752··on Understanding is the new bottleneck
Yes. That is what trust means. And being able to trust the right folks makes a good manager.
361994752··on Understanding is the new bottleneck
I’ve worked on both sides, so I know they’re actually very different.

As a manager, the first thing you do is get to know your people. Some of them will be very strong and trustworthy. You give them the hardest work, and you ask them the least. That’s how you scale your team’s scope without getting overburdened. And that’s why teams have key people.

But when you work with LLMs, you still need to understand most of the ideas yourself if it’s a serious product. Because in the end, it means nothing to “trust” an agent. You’re the one responsible for what you and the LLM ship.

361994752··on Gemini 3.7 Flash
I guess the demand is just too high... But even after the price hike, ds is still much cheaper?
361994752··on Mea Culpa – Dark Hours
Did you submit the other half? Which definitely would prove "dog ate my homework"
361994752··on AirLLM 70B inference with single 4GB GPU
I thought I met some huge breakthrough on computer science until I saw your comment
361994752··on 2x, not 10x: coding with LLMs in 2026
Now you actually have very long meetings with AI, if you consider all these long design / explorer / post-poc conversations "meetings".
361994752··on Kimi K3-256k
so Deutschland is not affected. Germany is
361994752··on U.S. government will decide who gets to use GPT-5.6
for a couple secs, i cannot tell if you are joking or it is true...
361994752··on GPT-5.4
i guess you still have the "auto" as an option to route your request
361994752··on CXMT has been offering DDR4 chips at about half the prevailing market rate
is CXMT attacking every contry?
361994752··on Blood oxygen monitoring returning to Apple Watch in the US
as some one whose family passed away due to pneumonia, spo2 is a life saving feature if we had that back then. probably 99.9% of the time spo2 number is good enough. but the value is really about the left 0.1% . of course the false positive rate should be low enough.
361994752··on Window Activation
I have my glasses and still got here :(
361994752··on Local-First Software Is Easier to Scale
It reminds me of that joke where young people see a floppy disk for the first time and say, "Oh, you 3D printed the save icon!" Might be reality very soon.
361994752··on Local-First Software Is Easier to Scale
It's amazing to me how we called "box-product" now has a fancy new name "local-first". "Box product" is quite well understood. It has a lot of benefits, but also the business model is harder to get right comparing to cloud services. For opensource projects, that will not be a problem tho.
361994752··on Jury awards American Airline $9.4M from website behind 'skiplagging' hack
Will this verdict stop Skiplagged from continuing its business in the future, either legally or financially? Or is it more like a one-time penalty they have to pay
361994752··on Pear AI founder: We made two big mistakes
I'm really interested. Could you kindly elaborate?
361994752··on Pear AI founder: We made two big mistakes
Apologies if this is a dumb question, but PearAI, Continue, and Cursor all seem like different versions of GitHub Copilot to me. Am I understanding that correctly? Why are we funding so many 'GitHub Copilot's?
Page 1 of 2Next →