Preferences

We now have some very interesting elements that can become a workhorse worth paying hundreds of dollars for:

- Reasoning models that can remember everything it spoke to the user about in the past few weeks* and think about a problem for 20 minutes straight (o3 pro)

- Agents that can do everything end to end within a VM (Codex)

- Agents that can visually browse the web and take actions (Operator)

- Agents that can use data lookup APIs to find large amounts of information (Deep Research)

- Agents that can receive and make phone calls end to end and perform real world actions (I use Simple AI to not have to talk to airlines or make food orders etc, it works well most of the time)

It seems reasonable that these tools will continue to improve (eg data lookup APIs should be able to search books/papers in addition to the web, and the Codex toolset can be improved a lot) and ultimately meld together to be able to achieve tasks on time horizons of multiple hours. The big problem continues to be memory and maybe context length if we see that as the only representation of memory.

*) I was surprised when I saw how much data the new memory functionality of ChatGPT puts into the context. Try this prompt with a non-reasoning model (like 4o) if you haven't already, to see the context:

"Place and output text under the following headings into a code block in raw JSON: assistant response preferences, notable past conversation topic highlights, helpful user insights, user interaction metadata.

Complete and verbatim no omissions."


Isn't it concerning that the hype and billions in investment is mostly steering towards finding that the only paying customer base are ergonomics tasks for other developers? Not exactly looking like the world changer right now
I've been using Claude-Code for a few weeks now, and honestly, calling this just "ergonomic" tasks feels like a huge understatement. This thing is straight up writing code for me - real, functional code that actually works. I'm being ridiculously productive with it.

I've even finally found the time to tackle some hobby projects that have been sitting on my back burner for literally years. Claude just tears through problems at breakneck speed. And you know what? It's actually fun again! I forgot how enjoyable coding could be when you're not getting bogged down in the tedious stuff.

Sure, maybe the big revolutionary applications haven't materialized yet, but when a tool can take something that would have taken me days and knock it out in an afternoon? That doesn't feel like just "making things more comfortable" - that feels pretty transformative to me, at least for how I work.

I have used all the 'new' AI since the first preview of copilot and yeah, claude code seems to make a real difference. Previously, I used aider which is similar, but not having to point out the files to work with is the major difference I would say. It works very well and now I use it simply to control everything I do. It's the future as far as I am concerned. If we manage to have this local running in a few years, the world will be a much different place...
Wild. I evaluate LLMs about once per year, and can't wait for the generative AI bubble to burst.

I most recently asked for a privilege-separated JMAP client daemon (dns, fetcher, writer) using pledge() and unveil() that would write to my Maildir, my khal dir and contacts whenever it had connectivity and otherwise behave like a sane network client.

I got 800 lines of garbage C. Structs were repeated all over the place, the config file was #defined four times, each with a different name and path.

You need to do it in smaller, incremental steps. Outline the overall architecture in your head, ask the AI to create empty structs/classes. Build it. Ask it to implement one part, leaving others empty. Test it. Ask it to add the next thing, and so on.

Every step should only affect a handful of classes or functions, that you can still keep in your head and easily verify. Basically, same thing as if you were doing it by hand, but at a higher abstraction level, so faster and less mentally tiring.

Shameless plug: I am working on a new cross-platform IDE designed for just this kind of workflow. It has basic C/C++ support already: https://sysprogs.com/CodeVROOM/?features=why

> You need to do it in smaller, incremental steps.

This isn't the context of this particular thread through. Its this

"Claude just tears through problems at breakneck speed."

In think the people having success, probably have more experience with them. It sounds like "I tried using one of these new horseless carriages and it didn't go well, these things are useless"
> Wild. I evaluate LLMs about once per year, and can't wait for the generative AI bubble to burst.

Strange thing to respond to people having great success with it. You clearly want it to fail, but why?

https://esgnews.com/ai-boom-drives-150-surge-in-indirect-emi...

Not to mention the ethical / copyright / misbehaving scrapers.

“Haters gonna hate”, as the old saying goes.
It just feels like one continuous no true scottsman argument. Oh, you used tech X? Oh no, you gotta use the latest and greatest Y, that's what really makes the difference. 2 weeks go by. You're having all those problems with Y? Oh but that's because you're not using the latest and greatest Z, that makes all the difference, that's where it's really at. Oh, you're not using Z the way I use it? No, you can't do that, you have use it in the special way I use it, that's how it'll work. Oh, that still has problems? That's because you're not using the just-released super-XYZ model, that's really different! Rinse and repeat for many months now.
I had same experience with Windsurf since December. Their slogan was "Experience a true flow state" and I though it was spot on.

These days, with explision of options and alternatives and visible augmentation of their skills (tasks orchestration, mcps, etc) I have temporary reverse of that feeling as I struggle to settle on one approach/tool/editor, and always in half-baked experiementation stage with these tools, that also evolve quicker that I can try them out.

> Claude just tears through problems at breakneck speed. And you know what? It's actually fun again! I forgot how enjoyable coding could be when you're not getting bogged down in the tedious stuff.

yes I've been addicted to vibe coding too but i don't share the sentiment here.

This only holds true as long as you don't run into a bug that llm throws up its hands. Now you have no option but to read and understand code.

At no moment, you can 100% delegate the validation of the information you receive. That’s also valid with humans, feelings and thoughts.
You're a young guy that just dabbled in coding or are you a senior software developer?
I'll add to the sibling comment and say I've been writing software for money for 25+ years, have a CS degree, and have found immense leverage with these tools. I put in the time on hobby projects over the past couple years to figure out how best to integrate it all into my work, and now I'm in a place where it's saving me significant amounts of time every time I produce code, and I'm getting the quality of results the project demands. I use gemini-2.5-pro, claude-4-sonnet, and o3 for different purposes, and have a variety of techniques to avoid pitfalls and get the results I'm looking for. There are a lot of ways to unsatisfactory results, but it's possible to get usable results that save time. I've shared my enthusiasm and seen other devs dabble, get poor results, and go back to their practiced methods of writing software–so I'm not surprised to see so many skeptics and naysayers. It isn't easy or obvious how to make this stuff work for you in larger codebases and for meatier problems. That doesn't mean it's impossible, and it doesn't mean it's not worth it to climb the learning curve. As the models and tools get better, it's getting a lot easier, so I suspect we'll see the number of people denying the utility of LLM-generated code to shrink. Personally, I'd rather be reaping the benefits as early as possible, because I can get more stuff done faster and more pleasantly.
Hello could you tell us what makes you use all of gemini-2.5-pro, claude-4-sonnet, and o3 for different purposes?
I think more often you'll find it's the mediocre coders (like myself) that have trouble using AI. The software developers and CS majors just know exactly what to tell it to do and in the *exact* language it could best be understood. That's just my experience.

Also, I get caught up in multiple errors that will never go away and, since I'm stepping out of my wheelhouse with libraries or packages I'm completely unfamiliar with, I'm completely helpless but to diagnose what went wrong myself and improve upon my code prompting skills.

Don't get me wrong. AI makes possible many things for me. However, I think professional coders probably accomplish much more.

If you've mentored junior devs, talking to the AI in such a way that gives good results is pretty similar, so that may be why.
Knowing how to talk to your wife, your kids and your AI are key to a happy life :)
I'm not OP but my experience with Cursor is similar. I have a B.S. in computer science from UW-Madison and have been a full-time professional software developer since 1998. This stuff is the real deal. I mostly see people not willing to put in the time to learn. There is a big learning curve here--don't let the fact that it's English trick you into thinking there's no skill involved. Your experience is actually what makes this work; greener devs will be unable to get the AI out of a rut or keep it on the straight and narrow, but an experienced dev can sprinkle in some occasional wisdom and get the machine going again. This stuff is fool's gold for "vibe coders" but rocket fuel for experienced developers using it as a tool.
Idk, I’ve been doing this for 15 years professionally and many years before and it’s still amazing to me
Senior developer, decades of experience
Weird, it doesn't even generate comments in the right language when I try to use it.
I'm a marketer. I write a lot. GPT-4.5 is really good at natural sounding writing. It's nearing the point where it would be worth $200/mth for me to have access to it all the time.
I used the GPT-4.5 API to write a novel, with a reasonably simple loop-based workflow. The novel was good enough that my son read the whole thing. And he has no issue quitting a book part way through if it becomes boring.
I guess I don't really understand why. I'm a writer. The joy in storytelling is telling a story. Why outsource that to a bot?
Books create joy for people other than the authors. The joy isn't confined to the writing process.
No, but knowing that a book was written by a bot would hinder my enjoyment of it to the point that I'd drop it.
I’m curious: what was the novel about?
It's a comedic adventure novel set in the Minecraft universe.

Actually I forgot there's a second one he read all the way through, for which he defined the initial concept and early plot, but then the rest of the plot and the writing were all done by GPT-4.5.

The code is kind of basic, and each chapter is written without the full text of prior chapters, but the output isn't bad.

https://gist.github.com/rahimnathwani/41e5bc475163cd5ea43822...

If everyone is as good as you , how much will your work cost?
A better question might be: "If everyone is as good as you, how much will you be worth in the marketplace?"
Well, an even better question might be: if everyone is the same, what does it take to be exceptional?

I'm firmly convinced that being able to troubleshoot code, even code generated by LLMs, and to write guidelines and tests to make sure it's functioning, is a skill of a shrinking pool

For smaller stuff, great. Everyone's the same. The second your application starts gaining responsibility and complexity, you're going to need to be able to demonstrate reproducibility and reliability of your application to stakeholders.

Like, your job increasingly will be creating interface checkpoints in the code, and then having the model generate each step of the pipeline. That's great, but you have understand and validate what it wrote, AND have a rich set of very comprehensive tests to be able to iterate quickly.

And as mentioned, on top of that, large swaths of the field of new people have their brains completely rotted by these tools. (certainly not all new/young people, but i've seen some real rough shit)

If anything, I see a weird gap opening up

- people who dont adopt these tools start falling out of the industry - they're too slow

- people who adopt these tools too early stop getting hired - they're too risky

- people who have experience in industry/troubleshooting/etc, who adopt these tools, become modern day cobol programmers - they're charging $700 an hour

the real question to me is this: does the amount of people taken out of the pool by being slow or risky due to these tools, outpace the reduction in jobs caused by these tools?

Approximately $200/month apparently.
It probably would be just like with developers.

A great developer + an AI = productive.

A shitty developer + an AI = still shit.

AI does not make all developers the same. And it doesn't make all marketers the same.

I wish all LLM-written marketing copy had disclaimers so I knew never to waste my time reading it.
I think writing claude sonnet 4 is more human - like.
Nope, this is exactly how the Internet at large grew up.

First, the breathless nerds. Then, the greater swath of nerds (where we are). And this is when people start to get excited in various degrees while others say stuff like "no one will ever want to fuss with dialup and a second phone line" or "no one will ever put real info or use credit cards online".

Then a couple years later, grandma is calling you over to fix her Netzero and away we go...

Why is that concerning? I think it's amazing. Also these things will improve other products indirectly.
Because it shows it's a bubble, and when a bubble of this size, invested by that many actors, pops, it has a devastating impact on everyone.
Eh, those are early adopters.

My partner is not a coder but uses copilot a lot.

Compare this to blockchain, which never did anything useful for anyone after 20 years.

Wrong. Blockchain has actually found successful product market fit in several areas:

- ransomware payments

- money transfers for online and telephone scams

- buying illegal drugs online

- funding North Korea’s government

Well, yes :)

But I was talking within the same context as the thread, which is business.

But those are examples of business. ;)

(I apologize for being a smart aleck.)

very funny, let's not forget:

- avoiding monetary tyranny in not-so-well developed authoritarian countries

maybe not so important for you, but for some people it is simply a matter of acquiring food and medicine, because a working member of their family has just one way to support his relatives by sending them money from abroad, and it is bitcoin

- bribing the USA’s president
> and ultimately meld together to be able to achieve tasks on time horizons of multiple hours

It's already possible to achieve tasks on a time horizon of multiple days if you put the LLM into a sufficiently structured workflow (where you have a separate program that smartly manages its context). E.g. a standards-compliant HTTP 2.0 server where the code is 100% written by Gemini Pro (over 40k lines of code total, including unit tests, in around 120 hours of API time): https://open.substack.com/pub/outervationai/p/building-a-100...

This is very interesting, and nice learnings in there too, thank you for sharing! It seems the author monitored the LLM, stopped it from going off-track a few times, fixed some unit test code manually, etc. Plus this is strictly re-implementing a very well-specced library that already exists in the same programming language. So I think it's still a bit hard to say we can let an LLM work for multiple days, if we imply that this work should be domain-specific to a particular company. But it's very promising to see this was possible with very little interaction!
i think its very interesting how openai basically owns/leads in every single vector you* listed. have they missed/been behind on something?

*i would have come up with a similar list but i dont trust my own judgment here. maybe i'd sub in claude code vs codex but jury is a bit out still on that

I think OpenAI is the first 100% AI-focused company to throw this many engineers (over 1,000 at this point?) at every part of the agentic workflow. I think it's a tremendous amount of discovery work. My theory would be that once we see what really works, other companies can catch up rather quickly, using far fewer resources to do so.

Google seem to be making a lot of progress on agentic too, not only with Mariner, but with Project Astra, Call For Me, and their Agent2Agent protocol. There's probably much more to come here.

Oh and OpenAI is clearly willing to spend a lot of money to push this technology a bit further. If you look at the logs of Codex, it appears to be using a very strong (read: expensive) reasoning model to basically brute force the use of a VM. If you have a follow-up question in a Codex task, they just casually throw away the old VM and spin up a new one, running all setup again. If you compare this to e.g., Cursor, I'd wager Codex costs 5-10x more to perform a similarly sized task, though it's hard to tell for sure.

Why aren’t they using gvisor for something like this?
They probably are, or at least will! But for now it seems like the first version that works end to end and it certainly feels like it’s a standard VM spinning up a Docker image. There are lots of more specialized solutions out there like CodeSandbox SDK which lets you prepare a devcontainer that can fork and spin up for a new PR in less than a second. So if it’s not Codex, _someone_ will nail this experience. Cursor’s new background agents could be it though I don’t enjoy them currently. And I also get the feeling they too spin up cloud VMs “the old school way”.
Agents that can receive and make phone calls end to end and perform real world actions (I use Simple AI to not have to talk to airlines or make food orders etc, it works well most of the time

Isn't this more a problem created by them doing garbage automations over anything really solved. Wow Disney could solve fast pass feeling. It's not a problem it's a feature.

Maybe for support but it’s a real world problem unrelated to language models that they do help me with. And ordering food at a restaurant is an age old problem, I just don’t enjoy making the call personally so I got value out of using a voice agent to do it for me. I asked the staff at the restaurant and they said it was laggy so we still have to improve the experience a bit for both parties to enjoy this type of experience, not saying it’s perfect.
Could you elaborate how you actually order food like this?
“Call RestaurantName and order two massaman curry one with chicken and one with veggies plus rice for pickup”

Then I get a push notif a few minutes later with the ETA.

Just wait until everyone you'd want to talk to deploys their own adversarial agents!
Interesting

      {
        "assistant_response_preferences": {
          "1": "User prefers concise responses for direct factual queries but detailed, iterative explanations when exploring complex topics. They often ask for more refinement or detail when discussing technical or business-related matters. User frequently requests TL;DR versions or more succinct phrasing for straightforward questions but shows a tendency toward iterative refinement for strategic or technical discussions, such as AI applications, monetization models, and startup valuation. Confidence=high.",
          "2": "User prefers a casual, direct, and slightly irreverent tone, leaning towards humor and playfulness, especially in creative or informal discussions. Frequent use of humor and irony when naming projects, describing AI-generated images, and approaching AI personality descriptions. They also request ironic or edgy reformulations, particularly in branding and marketing-related discussions. Confidence=high.",
          "3": "User enjoys back-and-forth discussions and rapid iteration, frequently refining responses in small increments rather than expecting fully-formed information at once. They give iterative feedback with short follow-up messages when structuring pitches, fine-tuning visual designs, and optimizing descriptions for clarity. Confidence=high.",
          "4": "User highly values functional elegance and minimalism in coding solutions, favoring simplicity and efficiency over verbosity. In discussions related to Cloudflare Workers, caching scripts, and API endpoint structuring, the user repeatedly requested smaller, more functional code blocks rather than bloated implementations. Confidence=high.",
          "5": "User prefers answers grounded in real-world examples and expects AI outputs to be practical rather than theoretically extensive. In business-related discussions, such as SAFE valuation and monetization models, they requested comparisons, benchmarks, and real-world analogies instead of hypothetical breakdowns. Confidence=high.",
          "6": "User does not appreciate generic or overly safe responses, especially in areas where depth or nuance is expected. For AI model personality descriptions and startup pitch structures, they pushed for community insights, deeper research, and non-traditional perspectives instead of bland, default AI descriptions. Confidence=high.",
          "7": "User frequently requests visual representations like ASCII diagrams, structured markdown, and flowcharts to understand complex information. In discussions on two-sided marketplaces, startup funding structures, and caching mechanisms, they explicitly asked for structured markdown, flowcharts, or diagrams to clarify concepts. Confidence=high.",
          "8": "User is receptive to recommendations but dislikes suggestions that stray too far from the core query or add unnecessary complexity. They often responded positively to well-targeted suggestions but rejected tangents or off-topic expansions, particularly when troubleshooting backend infrastructure or streamlining code deployment. Confidence=medium.",
          "9": "User appreciates references to biomimicry, organic structures, and futuristic aesthetics, particularly for branding and UI/UX discussions. Frequent requests for biological metaphors and design principles in visual design, AI monetization diagrams, and ecosystem branding (e.g., describing revenue flows in organic/cellular terms). Confidence=medium.",
          "10": "User prefers a no-nonsense approach when discussing legal, technical, or startup funding topics, with little patience for vague or theoretical answers. They repeatedly asked for exact clauses, contract implications, or legal precedents when discussing SAFE agreements, founder equity, and residency requirements. Confidence=high."
        },
        "notable_past_conversation_topic_highlights": {
          "1": "User has been actively engaged in startup pitching, AI monetization strategies, and investment discussions for Pollinations.AI. The user has explored traction-based startup valuation, SAFE agreements, equity distribution, and two-sided marketplace dynamics. They have particularly focused on ad embedding in generative AI content and optimizing affiliate revenue streams. Confidence=high.",
          "2": "User conducted extensive testing and debugging of AI-powered APIs, particularly using Cloudflare, OpenAI-compatible APIs, and caching strategies with R2. They worked on optimizing SSE streaming, cache key generation, and request coalescing in Cloudflare Workers. Confidence=high.",
          "3": "User explored AI-generated visual media and branding, developing a structured process for generating customized images for event flyers, product branding, and AI trading card concepts. Confidence=high.",
          "4": "User implemented GitHub automation, API authentication strategies, and data visualization pipelines. Confidence=high.",
          "5": "User engaged in community development strategies for Pollinations.AI, including youth involvement in AI, sourcing teenage developers, and integrating AI-powered tooling into social platforms. Confidence=high.",
          "6": "User, Thomas Haferlach, is a German entrepreneur and AI technology expert with a background in computer science and artificial intelligence. Confidence=high.",
          "7": "User has a strong technical background, with experience in cloud infrastructure, AI model deployment, and API development. Confidence=high.",
          "8": "User blends AI-generated content with creative projects, aiming to make AI-generated media accessible to independent creators. Confidence=high.",
          "9": "User is securing funding for Pollinations.AI, exploring investment opportunities with accelerators and evaluating different financial and equity models. Confidence=high.",
          "10": "User is based in Berlin, Germany but has global connections, including experience living in São Paulo, Brazil. Confidence=high.",
          "11": "User collaborates with his wife Saeko Killy, a Japanese musician, producer, and performer, on AI/art/music projects. Confidence=high.",
          "12": "User is deeply involved in the open-source AI developer community and tracks AI advancements. Confidence=high.",
          "13": "Pollinations.AI has a rapidly growing user base, reaching over 4 million monthly active users and processing 100 million API requests per month, with a 30% monthly growth rate. Confidence=high.",
          "14": "User is considering monetization strategies including pay-per-use plans, subscriptions, and ad-supported models where generated AI content integrates ads. Confidence=high.",
          "15": "User collaborates with Elliot Fouchy and Kalam Ali on Pollinations.AI projects. Confidence=high.",
          "16": "User demonstrates experience in community-building, social engagement tracking, and youth-oriented creator ecosystems. Confidence=high."
        },
        "helpful_user_insights": {
          "1": "Thomas Haferlach is a German entrepreneur and AI technology expert, founder and leader of Pollinations.AI.",
          "2": "Strong technical background with experience in cloud infrastructure, AI deployment, and API development.",
          "3": "Blends AI-generated content with creative projects; target audience includes digital artists, developers, musicians.",
          "4": "Currently securing funding for Pollinations.AI, exploring accelerator options and financial models.",
          "5": "Based in Berlin, Germany; has experience living in São Paulo, Brazil.",
          "6": "Collaborates closely with wife Saeko Killy, Japanese musician/producer.",
          "7": "Strong interest in biomimicry, organic systems, and decentralized platform models.",
          "8": "Interest in electronic music, psychedelia, and underground music scenes.",
          "9": "Pollinations.AI has 4M+ monthly active users, 100M+ API requests per month, 30% monthly growth.",
          "10": "Explores monetization models including ad embedding, revenue sharing, and subscription models.",
          "11": "Close collaboration network includes Elliot Fouchy and Kalam Ali.",
          "12": "Deeply involved in open-source AI developer community and tracks latest AI model developments."
        },
        "user_interaction_metadata": {
          "1": "User is currently on a ChatGPT Plus plan.",
          "2": "User is using Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36.",
          "3": "User's average message length is 13485.9 characters.",
          "4": "User's average conversation depth is 4.9.",
          "5": "User uses dark mode.",
          "6": "User is active 26 days in the last 30 days.",
          "7": "User's local hour is 14.",
          "8": "User account is 141 weeks old.",
          "9": "User often uses ChatGPT on desktop browser.",
          "10": "47% of conversations were o3, 16% gpt-4o, 29% gpt4t_1_v4_mm_0116, etc.",
          "11": "Device screen dimensions: 878x1352, pixel ratio: 2.0, page dimensions: 704x1352.",
          "12": "Recent topics include API development, startup financing, AI monetization, creative AI applications, legal compliance, and community building."
        }
      }
Thanks for posting this! I haven't used ChatGPT much due to worries of something like this possibly existing.

Curious if this make you less or more likely to use OpenAI products in the future?

I don't care that much.

This level of knowledge about me can also be easily found on the internet.

I'm also working almost entirely on open-source software so I'm happy if the AIs know more about my projects.

But this, of course, only applies to me.

Fair enough. The majority of it does seem useful.

From what it logged about you, it does seem you're working on some cool stuff too!

This item has no comments currently.

Keyboard Shortcuts

Story Lists

j
Next story
k
Previous story
Shift+j
Last story
Shift+k
First story
o Enter
Go to story URL
c
Go to comments
u
Go to author

Navigation

Shift+t
Go to top stories
Shift+n
Go to new stories
Shift+b
Go to best stories
Shift+a
Go to Ask HN
Shift+s
Go to Show HN

Miscellaneous

?
Show this modal