Hacker News: transformi

New comment by transformi in "I built ChatGPT with Minecraft redstone [video]"

transformi — Thu, 02 Oct 2025 18:39:27 +0000

Now create agents framework :)

New comment by transformi in "x402 — An open protocol for internet-native payments"

transformi — Tue, 23 Sep 2025 17:57:54 +0000

Looks like a competitor to the A2P that google released....

New comment by transformi in "K2-think: A parameter-efficient reasoning system"

transformi — Fri, 12 Sep 2025 22:37:03 +0000

So currently what are the best OSS reasoning models? (and how much compute the needed)

New comment by transformi in "Reusing Computation in Text-to-Image Diffusion for Efficient Image Generation"

transformi — Tue, 02 Sep 2025 15:40:45 +0000

Interesting approach! Remind me the early insights that neurons in DNN that capture similar concepts.

New comment by transformi in "New Stealth Model in Cline: "Sonic""

transformi — Wed, 20 Aug 2025 22:34:01 +0000

and due to simply asking it...:)

New comment by transformi in "Launch HN: Design Arena (YC S25) – Head-to-head AI benchmark for aesthetics"

transformi — Tue, 12 Aug 2025 16:19:45 +0000

Cool - do you train model that will be the proxy from the votes of persons?

New comment by transformi in "The Architecture Behind Lovable and Bolt"

transformi — Wed, 09 Jul 2025 21:26:01 +0000

i see they mostly offer api to run the sandbox on their infra...is there a way to host the sandboxes self hosted?(how much memory/compute needed?)

New comment by transformi in "The Architecture Behind Lovable and Bolt"

transformi — Wed, 09 Jul 2025 18:36:43 +0000

Looks like an ad... BTW there are more sandboxes code- here is OSS one: Daytona https://github.com/daytonaio/daytona

Ask HN: Is there open source platform like lovable?

transformi — Thu, 26 Jun 2025 18:19:22 +0000

I want to build something similar, is there any place to start with?

thanks

Comments URL: https://news.ycombinator.com/item?id=44389896

Points: 1

# Comments: 0

New comment by transformi in "Ask HN: What are you working on? (May 2025)"

transformi — Sun, 25 May 2025 21:45:52 +0000

Create alternative self-made feed of videos using VEO3 based on my intercation in social media.

New comment by transformi in "Gemini Diffusion"

transformi — Thu, 22 May 2025 01:30:21 +0000

Interesting to see if GROQ hardware can run this diffusion architecture..it will be two time magnitude of currently known speed :O

New comment by transformi in "Show HN: I used OpenAI's new image API for a personalized coloring book service"

transformi — Sat, 26 Apr 2025 01:05:13 +0000

Why don't you use canny/HED filter :O? (seems pretty overkill for this job..)

New comment by transformi in "Gemini 2.5 Flash"

transformi — Thu, 17 Apr 2025 19:34:25 +0000

Bad day is going on google.

First the decleration of illegal monopoly..

and now... Google’s latest innovation: programmable overthinking.

With Gemini 2.5 Flash, you too can now set a thinking_budget—because nothing says "state-of-the-art AI" like manually capping how long it’s allowed to reason. Truly the dream: debugging a production outage at 2am wondering if your LLM didn’t answer correctly because you cheaped out on tokens. lol.

“Turn thinking off for better performance.” That’s not a model config, that’s a metaphor for Google’s entire AI strategy lately.

At this point, Gemini isn’t an AI product—it’s a latency-cost-quality compromise simulator with a text interface. Meanwhile, OpenAI and Anthropic are out here just… cooking the benchmarks

New comment by transformi in "Ask HN: How to Use "Deep Research"?"

transformi — Mon, 07 Apr 2025 09:54:11 +0000

Searching for free coupons :)

New comment by transformi in "Benchmarking LLM social skills with an elimination game"

transformi — Mon, 07 Apr 2025 09:46:45 +0000

Interesting idea of ...maybe extend it to several ....to form a groups of secretes with different persons.

In Addition it will be interesting to extend a variation of the game that the players can use tools and execute code to take their preparation one step further.

New comment by transformi in "Perplexity Deep Research"

transformi — Sun, 16 Feb 2025 20:05:49 +0000

Thanks. I accept the criticism of being less digest and more opinionated. But at the end of the day it provide the same information.

Don't get me wrong - I don't mind to be copied on the Internet :), but I find this behavior quite rude, so I just mentioned it.

New comment by transformi in "Perplexity Deep Research"

transformi — Sun, 16 Feb 2025 01:06:26 +0000

You forgot Huggingface researchers - https://www.msn.com/en-us/news/technology/hugging-face-resea...

and BTW - I post an exact same spirit comment an hour ago... So I guess Today's copycat ethics aren't solely for products- but also for comment section . LOL.

New comment by transformi in "Perplexity Deep Research"

transformi — Sat, 15 Feb 2025 23:43:26 +0000

Since google, everyone trying replicate this feature... (OpenAI, HF..)

It's powerfull yes, so as asking an A.I and let him sythezise all what he fed.

I guess the air is out of the ballon from the big players, since they lack of novel innovation in their latest products.

New comment by transformi in "Anthropic achieves ISO 42001 certification for responsible AI"

transformi — Thu, 16 Jan 2025 05:12:59 +0000

Don't they need to show some proofs that their model indeed "responsible"? Why not everyone can get that certificate?

New comment by transformi in "Israel, Hamas reach ceasefire deal to end 15 months of war in Gaza"

transformi — Thu, 16 Jan 2025 01:05:21 +0000

Ok, Here is a reference for just one of the events -> https://www.bbc.com/news/articles/cdjgv1r4x81o