The last six months in LLMs in five minutes

Post by variodot » Tue, May 19, 2026, 12:10 PM UTC

magicalhippo wrote: post #92

Insanity wrote: post #10

I wonder how much the 'inflection point' is a thing vs marketing. I'm sure the models got somewhat better, but even now when I'm trying to 'vibe code' a game with the latest models (combination of Codex w/ gpt5.5 and gpt5.3-codex), they really do struggle. They definitely get something barebones up and running, but it's far from a fully fledged application.

I've "vibed" some non-trivial stuff lately using a combination of Codex with 5.5 and Claude Code with Opus 4.7. Key has been to spend a fair amount of time on initial overall design document, which is split into tangible and limited phases. I go back and forth between them on this document until we're all happy. For each phase an implementation plan is made. At the end, a summary document of what was delivered and wh…

Post by Glohrischi » Tue, May 19, 2026, 12:13 PM UTC

hollowturtle wrote: post #275

AussieWog93 wrote: post #267

Earlier quoted context omitted.

I don't really see your point. Most problems that people have aren't really super-novel, but just extremely bespoke. To give a specific example, 12 months ago I had a client pay me me to make a Chrome plugin that changed the rows in his Shopify Products page to display Quantity and SKU. These days you'd just one-shot it in Claude.

First of all it just underlines how shitty the web has become, second If that's your work I'd chase a career path where Claude can't one-shot this kind of dumb stuff

Post by Glohrischi » Tue, May 19, 2026, 12:18 PM UTC

hiw2d wrote: post #407

Glohrischi wrote: post #402

Earlier quoted context omitted.

I had a really fun day yesterday because anthropics limits on their normal 20$ subscription allowed me to play around for the whole day without hitting a limit. Its 'production' code because its a small browser game which has very small to 0 requirements on security and being perfect but high requirements on 'ever even doing this' and 'fun'. The code it generated hat 0 compiletime errors. I was able to descripe 10 th…

"We could already be at 95% at 'ai will take your coding job' without knowing because these 5% are so relevant." This is nonsense. Im not a SWE but a CEO, if that were true I'd be firing without a hitch. And yet this is not the activity we see. Why is that? Perhaps merely writing code is not the entire job.

Post by kstenerud » Tue, May 19, 2026, 12:18 PM UTC

embedding-shape wrote: post #414

kstenerud wrote: post #374

Earlier quoted context omitted.

> I did not much more than a cursory glance too, but found "./sandbox/create.go", a ~1300 lines long file with so much duplication even within just itself that I stopped counting. Really? What duplication did you actually find? I count a few small ones in buildMounts and ReadPrompt, maybe 20 lines or so, but hardly anything worthy of such an epithet. Admittedly, the parsing & escaping code and some utility functions…

The duplication I'm seeing isn't just "same text repeated" but structural duplication. Doing a quick 5 minute look again just to give you some pointers; runtime.MountSpec construction in buildMounts, Workdir vs aux-dir mount-mode handling, repeated one-off mount append blocks, overlay detection and so on, the list goes on. Just those should account for 200+ lines. Look for slight variations of the same thing but with…

Post by dominotw » Tue, May 19, 2026, 12:21 PM UTC

kstenerud wrote: post #219

hollowturtle wrote: post #209

> The coding agents got really good It's since november 2025, the so called "inflection point", that I'm still wondering for who coding agents become "really good". All I observe they got better at tool call and answering questions about big codebases, especially if the question has a vague pattern to search, and they're superuseful for that! For generating production code even with a lot of steering and baby sitting…

The polarization comes from the very disparate coding experiences and output quality that different people find when using these tools. For example, I've had the opposite experience of yours, generating very high quality work using Claude (such as https://github.com/kstenerud/yoloai ). Just in dealing with all the bugs and idiosyncrasies in the technologies I'm using, the agent has been a godsend in discovering and c…