fswd
Re:What's the strongest AI model you can train on a laptop in five min...
on Thursday August 14, 2025 @10:16AM (#44900662)
Right now, Qwen3 4B
Re:Is an Intel N100 or N150 a better value than a Raspberry Pi?
on Friday July 04, 2025 @02:46PM (#44466914)
I am reading this right now on my N100 desktop and it's 7W
Re:Wait. HOW MANY supernova explode every year?
on Tuesday April 15, 2025 @09:32PM (#43700466)
I've seen two super nova in my life time. once in 2008 and another in 2012
Re:serverless-registry: A Docker registry backed by Workers and R2
on Thursday September 05, 2024 @05:49PM (#41460673)
using this same architecture, it would be cool to build a serverless-git
Re:New 2GB Raspberry Pi 5 has 33% smaller die, 30% idle power savings
on Thursday August 29, 2024 @03:24PM (#41394408)
I probably have the same N100 miniforums and can only get it down to 7w. Is it possible you could share how you got it down to 3.6W and 4-8W?
I just got this N100 a few weeks ago, have it on a killawatt next to my desk.
Re:Cautionary tale on using Chase bank for indie business
on Friday August 23, 2024 @01:30PM (#41331027)
my story with them: Chase bank refused to cash their own Chase cashiers check. Seems crazy but I had to get a lawyer involved.
Re:OpenDevin: An Open Platform for AI Software Developers as Generalis...
on Sunday August 11, 2024 @12:12PM (#41217197)
yes that's the whole point of arxiv to allow anyone to publish.
Re:Show HN: Open-sourced Webflow for your own app
on Monday July 08, 2024 @01:35PM (#40907426)
> Some interesting challenges: 1. There is a React parser that is used to parse, insert the style, and serialize it back to code 2.
here's another approach I used with dynamic react
https://github.com/mhsdesign/jit-browser-tailwindcss "dynamic tailwind"
Re:New AI Training Technique Is Drastically Faster, Says Google
on Saturday July 06, 2024 @05:26PM (#40893442)
I've had the same exact experiences.
Re:Remix is better than GraphQL
on Sunday June 30, 2024 @01:37PM (#40838599)
this is so bizarre? I use GraphQL with Remix in my loader. It's a great combination. 7ms response from SQL. I can't understand the article. Sorry this person doesn't understand GraphQL nor Remix. might be AI generated
Re:We no longer use LangChain for building our AI agents
on Friday June 21, 2024 @08:53PM (#40755310)
The graph code, when all done and said, is identical for all scenarios.
Re:We no longer use LangChain for building our AI agents
on Friday June 21, 2024 @12:20PM (#40751072)
using LangGraph for a month, every single "graph" was the same single solution. The idea is cool, but it isn't solving the right problem.... (and the problem statement shouldn't be generating buzz on twitter. sorry to be harsh).
You could borrow some ideas from DSPy (which borrows from pytorch) their Module: def forward: and chain LM objects this way. LangGraph sounds cool, but is a very fancy and limited version of basic conditional statements like switch/if, already built into languages.
like something I'd use on my amiga 500 when I was a kid!
Re:Ask HN: Who wants to be hired? (May 2024)
on Wednesday May 01, 2024 @12:37PM (#40225653)
Location: West coast/remote
Remote: Yes
Willing to relocate: Texas or Florida
Technologies: AI/ML under DSPy, Guidance, Fullstack under Python/NodeJS, Supabase/GraphQL
Résumé/CV: 20 years professional experience
Email: [email protected]
Re:Supabase Storage: now supports the S3 protocol
on Friday April 19, 2024 @10:54PM (#40094320)
I just finished implementing S3 file upload in nextjs to cloudflare R2 with a supabase backend. Wish I had been lazy and waited a day!
Re:It's official: Europe turns to the Falcon 9 to launch its navigatio...
on Tuesday March 19, 2024 @09:00PM (#39761942)
These have to be spy satellites. GPS is just a timing signal, in space. Technology we had 40 years ago. There is no way you need $100M to build this and have special government authorization to collect the debris.
Re:WebSockets vs. Server-Sent-Events vs. Long-Polling vs. WebRTC vs. W...
on Monday March 18, 2024 @08:38PM (#39751767)
don't forget the timeout reconnect!
Re:Google's picture generator to relaunch due to criticism of inaccura...
on Monday February 26, 2024 @04:00PM (#39516737)
This story is heavily censored on hacker news
https://github.com/vitoplantamura/HackerNewsRemovals?tab=rea... (scroll down to bottom)
39465301 #25 3 points 0 comments -> Google Gemini leaked its woke prompt injection process
39465255 #1 78 points 1 comments -> Google to Pause Gemini Image Generation of People After Issues
39506022 #30 -> Gemini: Who negatively impacted society more, Elon Musk or Hitler?
39508833 #17 30 points 24 comments -> Losing Trust in Google
39516032 #15 8 points 6 comments -> Gemini and Google's Culture
Re:
on Saturday February 10, 2024 @01:27AM (#39324088)
stuff like this makes me want to experiment with going back to just one huge $100k server and running it all on one box in a server rack.
Re:OpenAI scrapped a promise to disclose key documents to the public
on Wednesday January 24, 2024 @03:21PM (#39122152)
OpenAI has broken every promise it has made
Re:Ask HN: How have you implemented human-in-the-loop workflows?
on Thursday January 11, 2024 @07:07PM (#38961562)
sorry I meant to say or explain computational graph, and yes langgraph was reintroduced recently last week.
Re:Ask HN: How have you implemented human-in-the-loop workflows?
on Thursday January 11, 2024 @04:20PM (#38959247)
Yes, I have implemented HITL. There's a task queue(psql skiplock). You make a request (insert row). It builds a "workflow graph" of your request and compiles it, a combination between a FSM and graph program. It runs an iteration on the workgraph, and then if successful, submits the next step in the queue as "pending". the user then inspects and accepts the tasks, which then run another iteration of the workgraph. If the user rejects it they can click "playground" and manually do the step.
Re:Samsung forecasts 85% drop in profit as chip sales falter
on Tuesday January 09, 2024 @05:45PM (#38933368)
I think they did several stock splits, and this time period was one of them
Re:Mixtral 8x7B: A sparse Mixture of Experts language model
on Monday January 08, 2024 @11:13PM (#38922225)
you cannot currently run mixtral with a 32k context on a 3090. Unless am I wrong? I think the largest context I was able to reproduce was around 1500 with 2 or 3 bit, I would have to look at my notes.
Re:Ask HN: What prevents Google from having the leading LLM?
on Tuesday December 12, 2023 @03:45PM (#38618214)
the management talent is preventing it
Re:Amazon Unveils Graviton4: A 96-Core ARM CPU with 536.7 GBps Memory ...
on Wednesday November 29, 2023 @07:17PM (#38467408)
I'm so glad we're seeing memory specs next to the core count, awesome.
Re:S3 Express Is All You Need
on Tuesday November 28, 2023 @04:34PM (#38451612)
I solved this problem locally. When uploading a file to the server before going to S3 it is cached in redis. Whenever the codebase needs to use the file, it checks redis, and if it is not there it fetches it and caches it again.
Re:Raspberry Pi 5 has no hardware video encoding and only HEVC decoding
on Monday October 30, 2023 @03:59PM (#38074874)
I just bought a 10th gen i5 laptop with 16gb of ram for $60 off of ebay. HP c640 chromebook. Fast enough to run a 7B LLM at 1-2 tokens/sec
Re:Hertz is scaling back its EV ambitions because its Teslas keep gett...
on Sunday October 29, 2023 @11:17PM (#38065313)
Tesla should make a fleet version that's easy to repair, and jump into the market place or help Hertz get back on its feet.
Re:Eclipse October 2023
on Friday October 20, 2023 @05:25PM (#37961735)
There's a partial lunar eclipse next week, October 28th
https://www.timeanddate.com/eclipse/lunar/2023-october-28