Hacker News: kumarm

A lot of the Moltbook stuff is fake

kumarm — Sat, 31 Jan 2026 17:47:46 +0000

Article URL: https://twitter.com/HumanHarlan/status/2017424292548673830

Comments URL: https://news.ycombinator.com/item?id=46838834

Points: 24

# Comments: 9

New comment by kumarm in "Show HN: Nano PDF – A CLI Tool to Edit PDFs with Gemini's Nano Banana"

kumarm — Sun, 30 Nov 2025 19:03:31 +0000

Amazing. Worked really well. Thank you.

New comment by kumarm in "Show HN: Nano PDF – A CLI Tool to Edit PDFs with Gemini's Nano Banana"

kumarm — Sat, 29 Nov 2025 23:36:53 +0000

Seems true and really wish the project included some sample PDF output.

My Text to Speech app uses bounding box to display what text in PDF is being read and would not work well PDF's from this project.

New comment by kumarm in "How the AI Bubble Will Pop"

kumarm — Thu, 02 Oct 2025 11:44:30 +0000

[even in programming it's inconclusive as to how much better/worse it makes programmers.]

Try building something new in claude code (or codex etc) using a programming language you have not used before. Your opinion might change drastically.

Current AI tools may not beat the best programmer, they definitely improves average programmer efficiency.

New comment by kumarm in "Show HN: ChartDB Agent – Cursor for DB schema design"

kumarm — Wed, 01 Oct 2025 16:34:00 +0000

The UI presentation of Schema is really nice. Is there a javascript based UI for web that is used?

New comment by kumarm in "Everything that's wrong with Google Search in one image"

kumarm — Thu, 25 Sep 2025 00:18:34 +0000

It is same on PlayStore and AppStore.

You would be surprised to know Apple started this in AppStore before Google on PlayStore. I assume it is because Google wanted to be safe from Antitrust lawsuits (Follow Apple rather than going there first).

New comment by kumarm in "Gemini 2.5 Flash Image"

kumarm — Wed, 27 Aug 2025 02:40:50 +0000

Latency. Started using API. Gets response directly on Gemini API in under 6 seconds. Fal.ai takes about 30 seconds.

New comment by kumarm in "Gemini 2.5 Flash Image"

kumarm — Tue, 26 Aug 2025 15:11:39 +0000

Since API currently is not working (seems rate limits not set for Image Generation yet) I tried on fal.

Definitely inferior to results I see on AI Studio and image generation time is 6s on AI Studio vs 30 seconds on Fal.AI

New comment by kumarm in "Gemini 2.5 Flash Image"

kumarm — Tue, 26 Aug 2025 14:58:11 +0000

Seems to be failing at API Calls right now with "You exceeded your current quota, please check your plan and billing details. For more information on this error,"

Hope they get API issues resolved soon.

New comment by kumarm in "Why does Kars4Kids sends most of its money to one town in New Jersey? (2023)"

kumarm — Sat, 28 Jun 2025 05:44:50 +0000

I am in Bay Area. I donated my cars to Kars4Kids before and even recommended to others since their process to donate is simple.

New comment by kumarm in "Builder.ai did not "fake AI with 700 engineers""

kumarm — Fri, 13 Jun 2025 16:55:34 +0000

Most likely. But that's exactly what someone who hasn't experienced enough cycles in industry would come up with :).

New comment by kumarm in "OpenAI to buy AI startup from Jony Ive"

kumarm — Wed, 21 May 2025 17:15:00 +0000

He is second only to Elon in this case (SolarCity, X/XAI).

New comment by kumarm in "Veo 3 and Imagen 4, and a new tool for filmmaking called Flow"

kumarm — Tue, 20 May 2025 23:44:29 +0000

All my Veo 3 videos has sound missing. No idea why. Seems like a common problem.

New comment by kumarm in "Google AI Ultra"

kumarm — Tue, 20 May 2025 19:26:13 +0000

So everyone who want Youtube Premium can explain to their boss why they need Gemini AI Ultra for work?

New comment by kumarm in "OpenAI Codex CLI: Lightweight coding agent that runs in your terminal"

kumarm — Wed, 16 Apr 2025 22:57:21 +0000

First experience is not great. Here are the issues to start using codex:

1. Default model used doesn't work and you get error: system OpenAI rejected the request (request ID: req_06727eaf1c5d1e3f900760d10ca565a7). Please verify your settings and try again.

2. You have to switch to model o4-mini-2025-04-16 or some other model using /model. Now if you exit codex, you are back to default model and again have to switch everytime.

3. Crashed the first time with NodeJS error.

But after initial hickups seems to work and still checking how good/bad it is compared to claude code (which I love except for context size limits)

New comment by kumarm in "Generate videos in Gemini and Whisk with Veo 2"

kumarm — Wed, 16 Apr 2025 00:03:15 +0000

Pretty disappointed with content moderation on Veo2. Here are the steps I did:

1. Took a picture of me and asked to describe person in the image.

2. Used Imagegen to create the cartoon version using description.

3. Tried to use veo-2.0-generate-001 to generate video of person in image (holding a coffee cup in original image) drinking coffee and having a conversation.

Video generation is blocked by content moderation.

Secretary of Education Calls AI 'A One'

kumarm — Fri, 11 Apr 2025 15:37:39 +0000

Article URL: https://twitter.com/factpostnews/status/1910072303334863141

Comments URL: https://news.ycombinator.com/item?id=43655076

Points: 9

# Comments: 2

New comment by kumarm in "GPT-4.5"

kumarm — Thu, 27 Feb 2025 23:03:33 +0000

Thank you. This is the best example of comparison I have seen so far.

New comment by kumarm in "O3 included in xAI Graphs for Model comparison"

kumarm — Tue, 18 Feb 2025 14:47:27 +0000

Where do I access grok3 reasoning model that xAI mentioned in the graph?

O3 included in xAI Graphs for Model comparison

kumarm — Tue, 18 Feb 2025 14:25:16 +0000

Article URL: https://twitter.com/12exyz/status/1891723056931827959

Comments URL: https://news.ycombinator.com/item?id=43089808

Points: 1

# Comments: 3