Hacker News: ismael_rr

New comment by ismael_rr in "GPT‑6 and Intelligent UI for everyone"

ismael_rr — Wed, 07 Oct 2026 19:21:00 +0000

I suspect that 6 sol was a better version of 5.6 terra (and note that in the 6 sol and luna release, they took out terra, and price 6 sol at 5.6 terra pricing), then the backlash from lesser capabilities made them roll out 6.1 sol as the actual 5.6 sol - size modee.

New comment by ismael_rr in "Mistral Large 4"

ismael_rr — Tue, 06 Oct 2026 14:54:45 +0000

Same with the US legal system protecting Anthropic from copyright laws from all the books and other stuff used for pretraining...

New comment by ismael_rr in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

ismael_rr — Wed, 30 Sep 2026 01:26:54 +0000

Distillation is also a broad term - I think most specifically, it refers to training a smaller model on a larger/better model's full output token distribution rather than normal pretraining, which only can access the next token in the data that was actually used.

It's also used to describe the SFT bootstrapping for posttraining, which is what people generally refer to as Chinese labs "distilling".

I would almost guarantee that smaller US frontier models (ex Luna/Sonnet) are distilled from their respective large models.

New comment by ismael_rr in "Show HN: Share your AI Setup, Learn from others"

ismael_rr — Thu, 17 Sep 2026 20:45:45 +0000

haha was also going to mention this at the risk of pedantry

New comment by ismael_rr in ">10x More Efficient Pretraining"

ismael_rr — Thu, 10 Sep 2026 15:52:33 +0000

Super awesome. Wish they would release the paper about what they did to achieve this. I remember nous released the token superposition paper which improved pretraining FLOPs some, but not 50x: https://nousresearch.com/token-superposition. Wondering if they also found some cool tokenization strategiesa

I gave frontier LLMs a canvas and told them to draw a self-portrait

ismael_rr — Wed, 19 Aug 2026 15:19:22 +0000

Article URL: https://ismaelroblesrazzaq.github.io/blog/llm-self-portraits/

Comments URL: https://news.ycombinator.com/item?id=49362780

Points: 3

# Comments: 3

New comment by ismael_rr in "Models Are Getting Dumber on Purpose"

ismael_rr — Sun, 16 Aug 2026 20:03:37 +0000

In my experience, it feels like this problem has been mostly solved. When I interact with a chatbot, I see it often uses web search to answer my questions and hallucinates much less then they used to. Furthermore, I suspect a lot of gains are merely from the system prompt instructing the chatbot to use web search to verify all facts it says.

New comment by ismael_rr in "Models Are Getting Dumber on Purpose"

ismael_rr — Sun, 16 Aug 2026 20:00:54 +0000

I agree that most AI use in terms of users may not be for coding or agentic use (everyday people are asking chatgpt for something or looking at google ai summary), but with respect to AI usage, I speculate that the vast majority of usage is coding and agentic because they're super token hungry.

In terms of the value proposition of AI replacing knowledge workers, all value is in coding agents (coding agents as general agents).

New comment by ismael_rr in "Ask HN: What are you working on? (August 2026)"

ismael_rr — Sun, 09 Aug 2026 23:35:14 +0000

for you tennis players out there, I'm working on RallyClip, an app for free tennis match segmentation. It's a free and open source alternative to SwingVision:

github: https://github.com/iroblesrazzaq/RallyClip website: rallyclip.app

I'm working on model performance and an iOS app right now; would love feedback on the macOS desktop app.

New comment by ismael_rr in "Show HN: Zanagrams"

ismael_rr — Sun, 28 Jun 2026 22:14:24 +0000

It was fun! I like how unlike the nyt games one, you can get additional information from the edges' existence. Would advise removing having both plural/singular forms of a word. Great work!