GPT-5.5 • Hacker News Board

Re: GPT-5.5

#511

Post by ComplexSystems » Thu, Apr 23, 2026, 10:08 PM UTC

ofjcihen wrote: post #470

sharts wrote: post #455

Earlier quoted context omitted.

One might argue that it’s not too too different from higher level abstractions when using libraries. You get things done faster, write less code, library handles some internal state/memory management for you. Would one be uneasy about calling a library to do stuff than manually messing around with pointers and malloc()? For some, yes. For others, it’s a bit freeing as you can do more high-level architecture without g…

I see this comparison made constantly and for me it misses the mark. When you use abstractions you are still deterministically creating something you understand in depth with individual pieces you understand. When you vibe something you understand only the prompt that started it and whether or not it spits out what you were expecting. Hence feeling lost when you suddenly lose access to frontier models and take a look…

It seems like some kind of technique is needed that maximizes information transfer between huge LLM generated codebases and a human trying to make sense of them. Something beyond just deep diving into the codebase with no documentation.

Re: GPT-5.5

#512

Post by deadbabe » Thu, Apr 23, 2026, 10:09 PM UTC

_alternator_ wrote: post #409

deadbabe wrote: post #342

Earlier quoted context omitted.

Given that it’s so easy, would you still do this same job if paid half as much?

No, I wouldn't. But most people won't have that choice; it doesn't work that way.

Companies could fire expensive engineers then just hire cheaper ones boosted with AI agents.

Re: GPT-5.5

#513

Post by xg15 » Thu, Apr 23, 2026, 10:09 PM UTC

sharts wrote: post #455

_alternator_ wrote: post #330

> One engineer at NVIDIA who had early access to the model went as far as to say: "Losing access to GPT‑5.5 feels like I've had a limb amputated.” This quote is more sinister than I think was intended; it likely applies to all frontier coding models. As they get better, we quickly come to rely on them for coding. It's like playing a game on God Mode. Engineers become dependent; it's truly addictive. This matches my o…

One might argue that it’s not too too different from higher level abstractions when using libraries. You get things done faster, write less code, library handles some internal state/memory management for you. Would one be uneasy about calling a library to do stuff than manually messing around with pointers and malloc()? For some, yes. For others, it’s a bit freeing as you can do more high-level architecture without g…

> Would one be uneasy about calling a library to do stuff than manually messing around with pointers and malloc()?

The irony is that the neverending stream of vulnerabilities in 3rd-party dependencies (and lately supply-chain attacks) increasingly show that we should be uneasy.

We could never quite answer the question about who is responsible for 3rd-party code that's deployed inside an application: Not the 3rd-party developer, because they have no access to the application. But not the application developer either, because not having to review the library code is the whole point.

Re: GPT-5.5

#514

Post by osti » Thu, Apr 23, 2026, 10:09 PM UTC

dataviz1000 wrote: post #468

snet0 wrote: post #439

Earlier quoted context omitted.

How are you handing the cube state to the model?

Does this answer the question? Opus 4.6 got the cross and started to get several pieces on the correct faces. It couldn't reason past this. You can see the prompts and all the turn messages. https://gist.github.com/adam-s/b343a6077dd2f647020ccacea4140... edit: I can't reply to message below. The point isn't can we solve a Rubik's Cube with a python script and tool calls. The point is can we get an LLM to reason about…

Can't they write a script to solve rubik cubes?

Re: GPT-5.5

#515

Post by jwrallie » Thu, Apr 23, 2026, 10:09 PM UTC

moritonal wrote: post #481

ofjcihen wrote: post #470

Earlier quoted context omitted.

I see this comparison made constantly and for me it misses the mark. When you use abstractions you are still deterministically creating something you understand in depth with individual pieces you understand. When you vibe something you understand only the prompt that started it and whether or not it spits out what you were expecting. Hence feeling lost when you suddenly lose access to frontier models and take a look…

I think it's more: when I don't have access to a compiler I am useless. It's better to go for a walk than learn assembly. AI agents turn our high-level language into code, with various hints, much like the compiler.

The difference is that there is a company that can easily take your agents away from you.

Re: GPT-5.5

#516

Post by nickandbro » Thu, Apr 23, 2026, 10:09 PM UTC

I just prompted GPT-5.5 Pro "Solve Nuclear Fusion" and it one shotted it (kidding obviously)

Re: GPT-5.5

#517

Post by erdaniels » Thu, Apr 23, 2026, 10:11 PM UTC

Schlagbohrer wrote: post #488

simonw wrote: post #195

This doesn't have API access yet, but OpenAI seem to approve of the Codex API backdoor used by OpenClaw these days... https://twitter.com/steipete/status/2046775849769148838 and https://twitter.com/romainhuet/status/2038699202834841962 And that backdoor API has GPT-5.5. So here's a pelican: https://simonwillison.net/2026/Apr/23/gpt-5-5/#and-some-peli... I used this new plugin for LLM: https://github.com/simonw/llm-op…

That's amazing that the default did that much in just 39 "reasoning tokens" (no idea what a reasoning token is but that's still shockingly few tokens)

If you don't know what a reasoning token is, then how can 39 be considered shockingly few?

Re: GPT-5.5

#518

Post by scottyah » Thu, Apr 23, 2026, 10:11 PM UTC

hapticmonkey wrote: post #507

davmar wrote: post #502

Earlier quoted context omitted.

i wonder if this is how engineers felt when the first electronic calculators came out and engineers stopped doing math by hand. did we feel uneasy that a new generation of builders didn't have to solve equations by hand because a calculator could do them? i'm not sure it's the same analogy but in some ways it holds.

The analogy would hold if there were 2 or 3 calculator companies and all your calculations had to be sent to them. If local models get good enough, I think it’s a very different scenario than engineers all over the world relying on central entities which have their own motives.

google/gemma-4-31B-it is honestly "good enough". It requires more than your current laptop for now, but it's not remotely inaccessible (especially if you're a SWE in the US)

Re: GPT-5.5

#519

Post by superfrank » Thu, Apr 23, 2026, 10:12 PM UTC

ofjcihen wrote: post #470

sharts wrote: post #455

Earlier quoted context omitted.

One might argue that it’s not too too different from higher level abstractions when using libraries. You get things done faster, write less code, library handles some internal state/memory management for you. Would one be uneasy about calling a library to do stuff than manually messing around with pointers and malloc()? For some, yes. For others, it’s a bit freeing as you can do more high-level architecture without g…

I see this comparison made constantly and for me it misses the mark. When you use abstractions you are still deterministically creating something you understand in depth with individual pieces you understand. When you vibe something you understand only the prompt that started it and whether or not it spits out what you were expecting. Hence feeling lost when you suddenly lose access to frontier models and take a look…

> When you use abstractions you are still deterministically creating something you understand in depth with individual pieces you understand

Hard disagree on that second part. Take something like using a library to make an HTTP call. I think there are plenty of engineers who have more than a cursory understanding of what's actually going on under the hood.

Re: GPT-5.5

#520

Post by bwhiting2356 » Thu, Apr 23, 2026, 10:12 PM UTC

_alternator_ wrote: post #330

> One engineer at NVIDIA who had early access to the model went as far as to say: "Losing access to GPT‑5.5 feels like I've had a limb amputated.” This quote is more sinister than I think was intended; it likely applies to all frontier coding models. As they get better, we quickly come to rely on them for coding. It's like playing a game on God Mode. Engineers become dependent; it's truly addictive. This matches my o…

You are now a manager. If your minions are out sick, project is delayed, not the end of the world.