Hacker News Reader

naivon Addendum to GPT-5 system card: GPT-5-Codex

https://help.openai.com/en/articles/11369540-using-codex-wit...

have to say not sure what this even means and what the exact definition of a message is in this context.

with claude code max20 I was constantly hitting limits, with codex not once yet

The model providers should analyse the tone of the instructions.

Before I finally gave up on Claude Code, I noticed that I got more aggressive towards it, the more stupid it got as I could not believe how dumb it started to be.

And I am sure I was not the only one.

naivon Incident Report for Anthropic

I think this is directly related to https://x.com/sama/status/1965110064215458055

And I think it was 100% on purpose that they degraded the model performance as Claude Code got so popular and they either ran out of capacity or were losing money too fast.

But now that people are fleeing to Codex as it improved so much during the time, they had to act now.

naivon GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search

same with google lens, I do understand the motivation / laws behind it but yes , it really is a let down.

naivon Anthropic raises $13B Series F

Same. We all moved to codex in the past weeks not looking back at our cancelled Max20 subscriptions.

But who knows what will be to best tool/model to use in October.

naivon Codex – OpenAI's coding agent – VSCode Extension

The past 3 releases of Codex have massively improved the user experience and output quality. I prefer it over Claude Code now and cancelled my Anthropic Max20 subscription in favor of Gpt Pro.

naivon Turning Claude Code into my best design partner

You can sign up for a subscription and pay from $20-$200 flat with some daily/weekly restrictions on token usage.

https://support.anthropic.com/en/articles/11145838-using-cla...

naivon Show HN: Omnara – Run Claude Code from anywhere

at the end he says "not just claude code. any agents"

naivon Token growth indicates future AI spend per dev

But he works 24/7 at then maybe 20x output

naivon Getting good results from Claude Code

The update to Opus 4.1 really improved the quality.

I personally really like to use Claude Code together with Zen MCP https://github.com/BeehiveInnovations/zen-mcp-server to analyse existing and review fresh code with additional eyes from Gpt5 and Gemini.

naivon Vibe coding is the fast fashion industry of software engineering

I think it's the opposite , the better you are as a coder and know your domain, the better you can use ai tools. someone with no expertise is set up for failure

naivon Gemini CLI

Who cares, software has no value anymore.

naivon Ask HN: How Do You Actually Use Claude Code Effectively?

the number one important thing: ask it to write tests first, then the code. and instruct it to not overmock or change code to make tests succeed.

besides this: I have great results in combination with https://github.com/BeehiveInnovations/zen-mcp-server but ymmv of course and it requires also o3 and gemini api keys but the token usage is really low and the workflow works really great if properly used

naivon Multiple Claude Code Sessions in an Easy UI: Crystal

I guess this will not work with a remote connection, or?

naivon Series C and Scale (Cursor)

so enough for them to build their own model

naivon Cursor 1.0

It has a totally different way of dealing with context

naivon Claude Code is now available to Pro plans

Yes, it can be a real pain.

You can use https://github.com/eyaltoledano/claude-task-master via mcp or eg https://github.com/Helmi/claude-simone

naivon Vibe coding for teams, thoughts to date

So the costs for Github actions cpu power should now be a limitation for test coverage?

naivon Claude Code SDK

played around with connecting https://github.com/eyaltoledano/claude-task-master via mcp to create a prd which basically replaces the ticket grooming process and then executing it with claude code creating a branch named like the ticket and pushing after having created the unit tests and constant linting.

naivon A Research Preview of Codex

to answer my own questions , it is actually laid out in chapter 6 of https://www.anthropic.com/engineering/claude-code-best-pract...

naivon A Research Preview of Codex

do you have then instance 2 and 3 listening to instance 1 with just a prompt? or how does this work?

naivon H3: For indexing geographies into a hexagonal grid, by Uber

This online tool gives you great idea about what this means on different levels:

https://wolf-h3-viewer.glitch.me/

naivon Musk-led group makes $97B bid for control of OpenAI

Yes, exactly, I thought this was clear. Thank you!

naivon Chat is a bad UI pattern for development tools

rather months than years

naivon OpenAI O3-Mini

It's called 'developer message' now

https://x.com/OpenAIDevs/status/1885407759887155301

naivon The impact of competition and DeepSeek on Nvidia

Groq lpu interference chip?

naivon The impact of competition and DeepSeek on Nvidia

Yes. close to free content

They understood the Dmca brilliantly so they did bulk cheap content purchases and hid behind the Dmca for all non licensed content which was "uploaded by users". They did bulk purchases of cheap content from some studios but that was just a fraction

Of course their risk of going advertise revenue only was high and in the beginning mostly only cam providers would advertise

Our problem was that we had contracts and close relationships with all the big studios so going the Dmca route would have severed these ties for an unknown risk. In hindsight not creating a company which did abuse the Dmca was the right decision. I am very loyal and it would have felt like cheating

Now it's a different story after the credit card shake down when they had to remove millions of videos and be able to provide 2257 documentation for each video

naivon The impact of competition and DeepSeek on Nvidia

I used to own several adult companies in the past. Incredible huge margins and then along came Pornhub and we could barely survive after it as we did not adapt.

With Deepseek this is now the 'Pornhub of AI' moment. Adapt or die.

naivon YC Graveyard: 821 inactive Y Combinator startups

Unfortunately the sheet seems to be not public

naivon IsMyXFeedFucked – Analyze How Your X Feed's Impacting You

Same. I follow more 'right' and see also balanced left.

Thus I was wondering why people were always talking about hate and racism on x.

Bluesky is a different story, there I exclusively see left wing content. Full of hate.