This is why I prefer models from Anthropic, especially for language-related tasks: they are more natural and to the point. GPT always used too much corporate-speak and market-speak, and this recent update looks terrible: I do not want my AI assistant to crack jokes, be sycophantic, or say "I’ve got you, Ron". I want it to assist me without pretending to be something that it isn't.
GPT-5.1: A smarter, more conversational ChatGPT
681–690 of 766 posts
Re: GPT-5.1: A smarter, more conversational ChatGPT
#682Doesn't look like it is upgraded, still shows GPT-5 in chatgpt. Anyone?
Looks like GPT-5.1 is here today, time to try it out
Re: GPT-5.1: A smarter, more conversational ChatGPT
#683Sadly, OpenAI models have overzealous filters regarding Cybersecurity. it refuses to engage on any thing related to it compared to other models like anthropic claude and grok. Beyond basic uses, it's useless in that regard and no amount of prompt engineering seems to force it to drop this ridiculous filter.
Can you give an example of things it refuses to answer in that subject?
The other day I wanted a little script to check the status of NumLock to keep it on. I frequently remote into a lot of different devices and depending on the system, NumLock would get toggled. GPT refused and said it would not write something that would mess with user expectations and said that it could potentially be used maliciously. Fuckin num lock viruses will get ya. Claude had no problem with it.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#684Earlier quoted context omitted.
I use K2 non thinking in OpenCode for coding typically, and I still haven't found a satisfactory chat interface yet so I use K2 Thinking in the default synthetic.new (my AI subscription) chat UI, which is pretty barebones. I'm gonna start trying K2T in OpenCode as well, but I'm actually not a huge fan of thinking models as coding agents — I prefer faster feedback.
I'm also a synthetic.new user, as a backup (and larger contexts) for my Cerebras Coder subscription (zai-glm-4.6). I've been using the free Chatbox client [1] for like ~6 months and it works really well as a daily driver. I've tested the Romanian football player question with 3 different models (K2 Instruct, Deepseek Terminus, GLM 4.6) just now and they all went straight to my Brave MCP tool to query and replied all…
I checked out chatbox and it looks close to what I've been looking for. Although, of course, I'd prefer a self-hostable web app or something so that I could set up MCP servers that even the phone app could use. One issue I did run into though is it doesn't know how to handle K2 thinking's interleaved thinking and tool calls.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#685Earlier quoted context omitted.
I think this is unethical. Humans have consistently underestimated the subjective experience of other beings. You may have good reasons for believing these systems are currently incapable of anything approaching consciousness, but how will you know if or when the threshold has been crossed? Are you confident you will have ceased using an abusive tone by then? I don’t know if flies can experience pain. However, I’m no…
I think current LLM chatbots are too predictable to be conscious. But I still see why some people might think this way. "When a computer can reliably beat humans in chess, we'll know for sure it can think." "Well, this computer can beat humans in chess, and it can't think because it's just a computer." ... "When a computer can create art, then we'll know for sure it can think." "Well, this computer can create art, an…
Just consider the context window
Tokens falling off of it will change the way it generates text, potentially changing its “personality”, even forgetting the name it’s been given.
People fear losing their own selves in this way, through brain damage.
The LLM will go its merry way churning through tokens, it won’t have a feeling of loss.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#686I don’t want more conversational, I want more to the point. Less telling me how great my question is, less about being friendly, instead I want more cold, hard, accurate, direct, and factual results. It’s a machine and a tool, not a person and definitely not my friend.
Think of a really crappy text editor you've used. Now think of a really nice IDE, smooth, easy, makes things seem easy.
Maybe the AI being 'Nice' is just a personality hack, like being 'easier' on your human brain that is geared towards relationships.
Or maybe Its equivalent of rounded corners.
Like the Iphone, it didn't do anything 'new', it just did it with style.
And AI personalities is trying to dial into what makes a human respond.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#687Earlier quoted context omitted.
I think the prompts might actually really useful for training, especially for generating synthetic data.
Yeah and that's a little more concerning than training to me, because it means employees have to read your prompts. But you can think of various ways they could preprocess/summarize them to anonymize them.
I don't think it means they have to read your prompt, but it's very probably that they would read some during debugging etc.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#688I'm excited to see whether the instruction following improvements play out in the use of Codex. The biggest issue I'e seen _by far_ with using GPT models for coding has been their inability to follow instructions... and also their tendency to duplicate-act on messages from up-thread instead of acting on what you just asked for.
I think thats part of the issue I have with it constantly. Let's say I am solving a problem. I suggest strategy Alpha, a few prompts later I realize this is not going to work. So I suggest strategy Bravo, but for whatever reason it will hold on to ideas from A and the output is a mix of the two. Even if I say forget about Alpha we don't want anything to do that, there will be certain pieces which only makes sense wit…
That's just how context works. If you're going to backpedal, go back in the conversation and edit your prompt or start a new session. I'll frequently ask for options, get them, then edit that prompt and just tell it to do whatever I decided on.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#689Earlier quoted context omitted.
It is interesting. I don't need ChatGPT to say "I got you, Jason" - but I don't think I'm the target user of this behavior.
The target users for this behavior are the ones using GPT as a replacement for social interactions; these are the people who crashed out/broke down about the GPT5 changes as though their long-term romantic partner had dumped them out of nowhere and ghosted them. I get that those people were distraught/emotionally devastated/upset about the change, but I think that fact is reason enough not to revert that behavior. AI…
> The target users for this behavior are the ones using GPT as a replacement for social interactions
And those users are the ones that produce the most revenue.
Re: GPT-5.1: A smarter, more conversational ChatGPT
#690I wish chatgpt would stop saying things like "here's a no nonsense answer" like maybe just don't include nonsense in the answer?
It might actually help output answer with less nonsense. As an example in some workflow I ask chatgpt to figure out if the user is referring to a specific location and output a country in json like { country } It has some error rate at this task. Asking it for a rationale improves this error rate to almost none. { rationale, country }. However reordering the keys like { country, rationale } does not. You get the wron…
This is/was a great trick for improving accuracy of small model + structured output. Kind of an old-fashoined Chain of Thought type of thing. Eg: I used this before with structured outputs in Gemini Flash 2.0 to significantly improve the quality of answers. Not sure if 2.5 Flash requires it, but for 2.0 Flash you could use the propertyOrdering field to force a specific ordering of JSONSchema response items, and force it to output things like "plan", "rationale", "reasoning", etc as the first item, then simply discard it.