Hacker News: robotswantdata

New comment by robotswantdata in "Small models also found the vulnerabilities that Mythos found"

robotswantdata — Sat, 11 Apr 2026 17:28:49 +0000

They found a nail in a small bucket of sand, vs mythos with the entire beach reviewed.

New comment by robotswantdata in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

robotswantdata — Mon, 06 Apr 2026 18:12:30 +0000

It’s as if it gives up, I respond keep going with original plan, you can do it champ!

New comment by robotswantdata in "GitHub has DMCA'd nearly all forks of the official Claude-code repo"

robotswantdata — Sat, 04 Apr 2026 10:28:46 +0000

Anthropic when they scrape the entire internet without permission: I sleep

Anthropic when their own source code ends up on GitHub: Real s**

New comment by robotswantdata in "Delve removed from Y Combinator"

robotswantdata — Sat, 04 Apr 2026 08:29:43 +0000

Seems crazy that anyone (startups and buyers) would trust these guys for audit.

Shows the “compliance theatre” of what SOC2 has become

New comment by robotswantdata in "RiskReady-open-source GRC platform with MCP gateway and human-approved mutations"

robotswantdata — Fri, 03 Apr 2026 13:12:41 +0000

The code smells very vibe coded in a bad way, sorry OP.

Interesting to use MCP for GRC but probably the most risk adverse to MCP segment to build in!

The security ratings in the readme are hilariously wrong

New comment by robotswantdata in "Show HN: Apfel – The free AI already on your Mac"

robotswantdata — Fri, 03 Apr 2026 12:30:07 +0000

Keep seeing similar mistakes with vibe coded AI & MCP projects. Even experienced engineers seem oblivious to this attack vector

New comment by robotswantdata in "April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini"

robotswantdata — Fri, 03 Apr 2026 10:57:08 +0000

Why are you using Ollama? Just use llama.cpp

brew install llama.cpp

use the inbuilt CLI, Server or Chat interface. + Hook it up to any other app

New comment by robotswantdata in "Lemonade by AMD: a fast and open source local LLM server using GPU and NPU"

robotswantdata — Thu, 02 Apr 2026 17:26:36 +0000

Forget all the vibe coded slop or Ollama. Lemonade is the real deal and very good, been using about a year now.

AMD are doing gods work here

New comment by robotswantdata in "Email obfuscation: What works in 2026?"

robotswantdata — Thu, 02 Apr 2026 12:01:49 +0000

Scrape normally collect emails, if no email seen take screenshot and OCR OCR is cheap and REGEX is cheap

New comment by robotswantdata in "Email obfuscation: What works in 2026?"

robotswantdata — Thu, 02 Apr 2026 10:00:16 +0000

How does that work if the scraper takes a screenshot to feed to a LLM or OCR?

New comment by robotswantdata in "TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS"

robotswantdata — Wed, 01 Apr 2026 19:34:51 +0000

Feels 100% vibe coded in a bad way.

Llama.cpp already has KV compression and one of the turbo quant PRs will get merged at some point.

If you don’t care about the fancy 3 bit, the q8 KV compression is good enough! Don’t bother with q4

./build/bin/llama-server -m model.gguf \ --cache-type-k q8_0 \ --cache-type-v q8_0 \ -c 65536

Etc

New comment by robotswantdata in "Show HN: Postgres extension for BM25 relevance-ranked full-text search"

robotswantdata — Tue, 31 Mar 2026 22:08:57 +0000

“Just use Postgres” greybeards right again. Looking forward to giving this a go soon

TAL emulation of the Roland Jx-8P synth

robotswantdata — Tue, 31 Mar 2026 15:49:35 +0000

Article URL: https://tal-software.com/products/tal-j8x

Comments URL: https://news.ycombinator.com/item?id=47589184

Points: 2

# Comments: 0

New comment by robotswantdata in "Ollama is now powered by MLX on Apple Silicon in preview"

robotswantdata — Tue, 31 Mar 2026 07:48:36 +0000

Why are people still using Ollama? Serious.

Lemonade or even llama.cpp are much better optimised and arguably just as easy to use.

New comment by robotswantdata in "Show HN: Sheet Ninja – Google Sheets as a CRUD Back End for Vibe Coders"

robotswantdata — Mon, 30 Mar 2026 08:07:24 +0000

Costs a lot? It’s a bargain for globally resilient infrastructure.

db-f1-micro is about $10pm inc storage for something that just works and can scale, be shifted on prem etc. you can run all your vibe coded slop on one instance.

New comment by robotswantdata in "Show HN: Sheet Ninja – Google Sheets as a CRUD Back End for Vibe Coders"

robotswantdata — Sun, 29 Mar 2026 20:36:58 +0000

Google have you covered: https://www.youtube.com/watch?v=Kl8ig2BtLAY

New comment by robotswantdata in "Show HN: Sheet Ninja – Google Sheets as a CRUD Back End for Vibe Coders"

robotswantdata — Sun, 29 Mar 2026 12:46:18 +0000

setup a DB project , use same cloud sql instance for all DBs. Did that for years on non prod or experimental projects. $100 is a bargain for what you get in terms of resiliency

New comment by robotswantdata in "Show HN: Sheet Ninja – Google Sheets as a CRUD Back End for Vibe Coders"

robotswantdata — Sun, 29 Mar 2026 12:18:13 +0000

Cloud sql lowest tier is pennies a day, this ninja platform is also not free.

A spreadsheet is a misclick away from corruption, why not spend another prompt on getting Claude to configure a db?

New comment by robotswantdata in "Show HN: Sheet Ninja – Google Sheets as a CRUD Back End for Vibe Coders"

robotswantdata — Sun, 29 Mar 2026 12:05:35 +0000

Don’t really get the purpose for this apart from throw away projects.

For vibe coders is it really “hours” setting up a database these days? GCP cloud sql + drizzle ORM is minutes and actually scales unlike a spreadsheet, heck Claude can even write you a deployment script and run it over GCP CLI.

New comment by robotswantdata in "Apple discontinues the Mac Pro"

robotswantdata — Fri, 27 Mar 2026 07:24:42 +0000

DGX workstations, expensive but allow PCI cards as well.

https://marketplace.nvidia.com/en-us/enterprise/personal-ai-...