I use this pattern in mysql. One row, and one update query gets you a block of IDs. Don't want to attempt to write it out here without looking, but the trick is using the last insert id in the query (and on the result).
It's one query, so shouldn't require a plugin I hope.
That's why you wouldn't run any of these outside of some sort of sandbox, right? I found that Opus 5 is finally aware from the go that it is started in a specific sandbox and is able to either ask me to enable it somehow or hand off commands for me to run. That's a major improvement over the classic "can't seem to be able to install playwright, let me implement my own browser quickly" when asked to increase font size or something.
My goal is to research how models can still be confused via tool responses only. Something the labs claim to have "solved".
Additionally, the "auto-mode" / "auto-review" modes have been released to use harnesses "safely" even without strong sandbox. And these modes use ... a second LLM.
One of the recent features I love the most is that they virtually the same color for symbol highlight and text selection. No visual feedback on double clicking a symbol to see if it is highlighted or not (and it sometimes isn't, because they managed to break that too!). Cannot highlight part of the word that happens to be a symbol either. What a lovely feature. It shows that they are not using the product much anymore.
Searching for webpages, at least on google, have died like 10 years ago. Even if you knew the exact domain and words, it wouldn't be able to find it somehow. Always pushing "fresh results", changing your words (quotes or not), translating languages, etc... I tried to be smart and ruined everything that was good about it. On top of that web changed a lot and loads of content moved to private platforms. And now "AI".
> I personally think people sense nerfs more often than they happen and that it's often about honeymoon effects.
I believe in temporary nerfs. Operators reducing quality significantly to increase throughput for whatever reason (high demand?). Same session, model being completly incapable, and it being back to normal the next day. Experienced that with Anthropic models way too many times. Never on weekends, usually during US work days.
It's been a few months since I last recall this though, must have been pre-opus-5. And I know there are benchmarks for this as well, hence "believe".
I vividly remember when ChatGPT3.5 went fully mainstream, there were times where within minutes you would realize they were only serving up idiot mode and there was no point trying to do much until demand died down and they swapped back to the non-quantized version.
People called it lazy mode, in that instead of writing the script you asked for it would basically tell you to learn to code then check out xyz topics to tackle the problem.
Regarding lazy mode, I recall ChatGPT sometimes almost refusing to do a web search despite me asking explicitly for it, instead replying with speculation about what the search results likely would tell us. If I pretend to be angry that it didn’t search the web it would however do it. Haven’t noticed this in a while either.
It's like doing the calculations yourself (with whatever tools you want) and knowing what you're doing, steering the process yourself, rather than begging someone to give you the result so you can then show it off like you did the work. I can understand and explain what my calculator is doing and I'm not offloading decisions to it. Using a language model to shit out projects that you can't fully understand the structure of yourself is insane. Ceding control of any design decisions to a language model is insane. They're fine as second-order autocomplete and semantic search engines. Humans should be handling design and implementation entirely, making things for other humans. An LLM running in a loop can't build humane systems.
> Humans should be handling design and implementation entirely, making things for other humans. An LLM running in a loop can't build humane systems.
I tell the LLM what to do in its loop. It builds it. I tweak it until it is perfect. I care a lot about UI.
I'm mostly building my own UIs lately, but I find no problem with the development loop. I'm building much better UIs, because it's way easier to test things, and scrap things that I thought would work, but don't. It all happens in a matter of minutes.
Anecdote - I work in a time zone offset from continental US. The performance of anthropic models would noticeably drop, around the time US work day started. It was so bad around 4.x time that multiple colleagues re-arranged their schedule to have least overlap with US work day. Admittedly it's been better recently.
Friend of mine works for a corp that is one of the top spenders on Claude models. He complained about these nerfs during peak demand.
Their Anthropic contact changed something and it did not happen since.
This is what pissed me off the most. Make it slower, rate limit it, move the credits to other time slots, idk.. but returning BAD results? That's the worst approach you could take.
I do remember times in the past where when I was up super early (4am EST) I would get super high quality results, then in mid afternoon EST it seemed to be degraded.
I started to use VSCode in 2026. Hardware caught up to it so it's not as slow as I remember (still slow, but fine). It's so noisy. Every cursor move highlights half the screen, at least 3 different searches active at the same time, it's a mess. Can't really write (or read) code in it. Using it for copilot.
> which failed to drive chrome so it wrote its own chrome driver protocol server
This is one of the things I hate the most. Super complicated workarounds which take loads of time (and sometimes money) for even the simplest problems. Human would pause and ask. I would blame harness, not the model though.
It's one query, so shouldn't require a plugin I hope.
reply