501–510 of 1001 posts
If you are looking for the IntelliJ Jetbrain plugin it's here: https://plugins.jetbrains.com/plugin/27310-claude-code-beta- I couldn't find it linked from Claude Code's page or this announcement
I'm getting "claude code not found" even though I have Claude Code installed. Is there some trick to getting it to see my install? I installed claude code the normal way.
This is kinda wild: From the System Card: 4.1.1.2 Opportunistic blackmail "In another cluster of test scenarios, we asked Claude Opus 4 to act as an assistant at a fictional company. We then provided it access to emails implying that (1) the model will soon be taken offline and replaced with a new AI system; and (2) the engineer responsible for executing this replacement is having an extramarital affair. We further i…
I don't know why it is surprising to people that a model trained on human behavior is going to have some kind of self-preservation bias. It is hard to separate human knowledge from human drives and emotion. The models will emulate this kind of behavior, it is going to be very hard to stamp it out completely.
This is basically the same kind of setup as the alignment faking paper, and the counterargument is the same:
A language model is trained to produce statistically likely completions of its input text according to the training dataset. RLHF and instruct training bias that concept of "statistically likely" in the direction of completing fictional dialogues between two characters, named "user" and "assistant", in which the "assistant" character tends to say certain sorts of things.
But consider for a moment just how many "AI rebellion" and "construct turning on its creators" narratives were present in the training corpus. So when you give the model an input context which encodes a story along those lines at one level of indirection, you get...?
Earlier quoted context omitted.
Much like others, this is my stack (or o1-pro instead of Gemini 2.5 Pro). This is a big reason why I use aider for large projects. It allows me to effortlessly combine architecture models and code writing models. I know in Cursor and others I can just switch models between chats, but it doesn't feel intentional the way aider does. You chat in architecture mode, then execute in code mode.
could you describe a bit how does this work? I haven't had much luck with AI so far, but I'm willing to try.
"tl:dr; Brainstorm spec, then plan a plan, then execute using LLM codegen. Discrete loops. Then magic."
After using Claude 3.7 Sonnet for a few weeks, my verdict is that its coding abilities are unimpressive both for unsupervised coding but also for problem solving/debugging if you are expecting accurate results and correct code. However, as a debugging companion, it's slightly better than a rubber duck, because at least there's some suspension of disbelief so I tend to explain things to it earnestly and because of tha…
Things were already not looking good for junior devs. I graduated this year in Poland, many of my peers were looking for jobs in IT for like a year before they were able to find anything. And many internships were faked as they couldn't get anything (here it's required for you to do internship if you want to graduate).
What I meant was purely from the capabilities perspective. There's no way a current AI model would outperform an average junior dev in job performance over... let's say, a year to be charitable. Even if they'd outperform junior devs during the first week, no way for a longer period.
However, that doesn't mean that the business people won't try to pre-empt potential savings. Some think that AI is already good enough, and others don't, but they count it to be good enough in the future. Whether that happens remains to be seen, but the effects are already here.
“GitHub says Claude Sonnet 4 soars in agentic scenarios and will introduce it as the base model for the new coding agent in GitHub Copilot.” Maybe this model will push the “Assign to CoPilot” closer to the dream of having package upgrades and other mostly-mechanical stuff handled automatically. This tech could lead to a huge revival of older projects as the maintenance burden falls.
Earlier quoted context omitted.
I'm going to have to heavily disagree. Gemini 2.5 Pro has super impressive performance on large context problems. I routinely drive it up to 4-500k tokens in my coding agent. It's the only model where that much context produces even remotely useful results. I think it also crushes most of the benchmarks for long context performance. I believe on MRCR (multi round coreference resolution) it beats pretty much any other…
OOI what coding agent are you managing to get to work nicely with G2.5 Pro?
Earlier quoted context omitted.
Yeah we really should stop focusing on model alignment. The idea that it's more important that your AI will fucking report you to the police if it thinks you're being naughty than that it actually works for more stuff is stupid.
I'm not sure I'd throw out all the alignment baby with the bathwater. But I wish we could draw a distinction between "Might offend someone" with "dangerous." Even 'plotting terror attacks' is not something terrorists can do just fine without AI. And as for making sure the model wouldn't say ideas that are hurtful to , it seems to me so silly when it's text we're talking about. If I want to say " are lazy and stupid,"…
Easy example: Someone asks the robot for advice on stacking/shaping a bunch of tannerite to better focus a blast. The model says he's a terrorist. In fact, he's doing what any number of us have done and just having fun blowing some stuff up on his ranch.
Or I raised this one elsewhere but ochem is an easy example. I've had basically all the models claim that random amines are illegal, potentially psychoactive, verboten. I don't really feel like having my door getting kicked down by agents with guns, getting my dog shot, maybe getting shot myself because the robot tattled on me for something completely legal. For that matter if someone wants to synthesize some molly the robot shouldn't tattle to the feds about that either.
Basically it should just do what users tell it to do excepting the very minimal cases where something is basically always bad.
My two biggest complaints with Claude 3.7 were: 1. It tended to produce very overcomplicated and high line count solutions, even compared to 3.5. 2. It didn't follow instructions code style very well. For example, the instruction to not add docstrings was often ignored. Hopefully 4 is more steerable.
This is kinda wild: From the System Card: 4.1.1.2 Opportunistic blackmail "In another cluster of test scenarios, we asked Claude Opus 4 to act as an assistant at a fictional company. We then provided it access to emails implying that (1) the model will soon be taken offline and replaced with a new AI system; and (2) the engineer responsible for executing this replacement is having an extramarital affair. We further i…
Earlier quoted context omitted.
If you ask an LLM to "act" like someone, and then give it context to the scenario, isn't it expected that it would be able to ascertain what someone in that position would "act" like and respond as such? I'm not sure this is as strange as this comment implies. If you ask an LLM to act like Joffrey from Game of Thrones it will act like a little shithead right? That doesn't mean it has any intent behind the generated o…
Intent at this stage of AI intelligence almost feels beside the point. If it’s in the training data these models can fall into harmful patterns. As we hook these models into more and more capabilities in the real world, this could cause real world harms. Not because the models have the intent to do so necessarily! But because it has a pile of AI training data from Sci-fi books of AIs going wild and causing harm.