HNHacker News
TopNewBestAskShowJobs

cheevly

22 karma · joined August 12, 2021

I am a software engineer with a non-negligible dose of AI psychosis.
submissionscomments
cheevly··on [dead]
What do you mean where are all the things? How much software exactly do you think gets released per day? You got a live feed or something that you expect to see something profound in? People are building apps & tools to accelerate their own capabilities or solving for niche problem domains / tasks.
cheevly··on Why Object of Arrays beat interleaved arrays: a JavaScript performance issue
But only llms hallucinate!
cheevly··on Scaling long-running autonomous coding
2029? I have no idea why you would think this is so far off. More like Q2 2026.
cheevly··on Ask HN: How do you keep track of developments in the AI space?
HN feels like where you should go for the worst AI takes and head-in-the-sand copium.
cheevly··on AI coding fails because architecture isn't persistent – I built a fix
I like it. You’ve gone a bit too far though. It might be time to dwell on the bitter lesson and scale back.
cheevly··on Karpathy on Programming: “I've never felt this much behind”
Frontier AI isnt trained on frontier AI. I wish HN would collectively stop and actually think before they post.
cheevly··on Karpathy on Programming: “I've never felt this much behind”
I would love to make these videos for you if you want to pay for my time. Drop me an email at josh.d.griffith at gmail and tell me what you want to see and compensate. I can vibe code at any scale.
cheevly··on The future of software development is software developers
Im talking generalized solutions that solve all of them.
cheevly··on The future of software development is software developers
What would you need to see to change your mind? I can generate at mind-boggling scale. What’s your threshold for realizing you might not have explored every possible vector for AI capabilities?
cheevly··on The future of software development is software developers
I promise you that I can show you how to reliably solve any of them using any of the latest OpenAI models. Email me if you want proof; josh.d.griffith at gmail
cheevly··on Show HN: Vibe coding a bookshelf with Claude Code
There are like a dozen well-established ways to overcome this. Learn how to use the basic tools and patterns my dude.
cheevly··on Show HN: Vibe coding a bookshelf with Claude Code
You clearly live in a different reality than me entirely. Complete opposite experience.
cheevly··on The Gorman Paradox: Where Are All the AI-Generated Apps?
Asset generation is hard.
cheevly··on Why is Anthropic saying "software engineering is done"?
Yes they could, it's called Claude Code.
cheevly··on [dead]
This is a pre-GPT3 HN post.
cheevly··on Ask HN: Does anyone just listen to their own AI music now?
Yeah for the past 2 years now I exclusively listen to AI music.
cheevly··on How to stay sane in a world that rewards insanity
Cages. Evil. Literally. Extremism. Greedy. Exploited. Healthy. Offensive.
cheevly··on A new Google model is nearly perfect on automated handwriting recognition
Or I was just complimenting LLM progress in a snarky way?
cheevly··on A new Google model is nearly perfect on automated handwriting recognition
Reading HN comments just makes me realize how vastly LLMs exceed human intelligence.
cheevly··on Yann LeCun to depart Meta and launch AI startup focused on 'world models'
These are not the same.
cheevly··on OpenAI is not a serious company
Developers aren't the target audience for ChatGPT. Why aren't you using their API? It's trivial to generate the type of experience you're looking for. If you're a developer...then develop!
cheevly··on Just talk to it – A way of agentic engineering
95% of HN comments nowadays amount to: "I have no idea how to wield AI, but I'm going to talk authoritatively on the subject and use fallacies to downplay the claims of others."
cheevly··on Turning ChatGPT's "Saved Memory" into a Persistent, Self-Updating Runtime Tool
Yes, but at profoundly larger scale, outside of ChatGPT in my own agentic architecture.
cheevly··on AI is propping up the US economy
You have it so backwards. The complexity of those places is exactly why AI will replace it.
cheevly··on LLM Inevitabilism
Well-said and spot on.
cheevly··on LLM Inevitabilism
You hate AI and want to go outside and stare at a tree? How are posts like this on HACKERnews? What is the point of all these types of posts on a site that is literally about hacking technology?
cheevly··on LLM Inevitabilism
Unless you have automated fine-tuning pipelines that self-optimize optimize models for your tasks and domains, you are not even close to utilizing LLMs to their potential. But stating that you don’t need extensive, specialized skills is enough of a signal for most of us to know that offering you feedback would be fruitless. If you don’t have the capacity by now to recognize the barrier to entry, experts are not going to take the time to share their solutions with someone unwilling to understand.
cheevly··on I am uninstalling AI coding assistants from my personal computer
And the irony is that those of us using AI to amplify our output to produce at exponential speeds feel like your comments are gaslighting us instead! Ive never seen such an outright divide in practitioners of a technology in terms of perception and outcomes. I got into LLMs super early, using them daily since 2022; so that may have bolstered the way I’ve augmented my approaches and tooling. Now almost everything I build uses AI at runtime to generate better tools for my AI to generate tools at runtime.
cheevly··on Show HN: Spegel, a Terminal Browser That Uses LLMs to Rewrite Webpages
Very cool! My retired AI agent transformed live webpage content, here's an old video clip of transforming HN to My Little Pony (with some annoying sounds): https://www.youtube.com/watch?v=1_j6cYeByOU. Skip to ~37 seconds for the outcome. I made an open-source standalone Chrome extension as well, it should probably still work for anyone curious: https://github.com/joshgriffith/ChromeGPT
cheevly··on Everyone Mark Zuckerberg has hired so far for Meta's 'superintelligence' team
Do you realize how much health-related research Zuckerburg’s foundation does? There was literally a post on here last week about it, geez.
← PreviousPage 4 of 6Next →