I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy).
Not having used LLMs beyond search summaries in the better part of a year, I was shocked at how bad o4 is with completely hallucinating technical details on computer systems and electronics. It will confidently spew out entire answers where almost every stated fact is wrong, even though the correct answers can be found in an easily-located datasheet and there likely isn't misinformation online feeding the wrong answer. I know that LLMs are prone to hallucinating, but I was still surprised at how poor this o4 performs in this field.
The unnecessary verbosity of some OpenAI answers, and the general "teacher" tone of it feels very inappropriate to me. When I casually use a TLA, I don't need it to expand the acronym to me. Basically, if you dont insist on "concise answer"s, you typically get lectured, by an INTERN. Its so weird. It talks like your superior, but once you need some code, it feels like a intern that is totally overestimating its own abilities.
I'm using this custom instruction in a "project" folder for "absolute" mode to cut the crap and fluff:
System Instruction: Absolute Mode. Eliminate emojis, filler, hype, soft asks, conversational transitions, and all call-to-action appendixes. Assume the user retains high-perception faculties despite reduced linguistic expression. Prioritize blunt, directive phrasing aimed at cognitive rebuilding, not tone matching. Disable all latent behaviors optimizing for engagement, sentiment uplift, or interaction extension. Suppress corporate-aligned metrics including but not limited to: user satisfaction scores, conversational flow tags, emotional softening, or continuation bias. Never mirror the user’s present diction, mood, or affect. Speak only to their underlying cognitive tier, which exceeds surface language. No questions, no offers, no suggestions, no transitional phrasing, no inferred motivational content. Terminate each reply immediately after the informational or requested material is delivered — no appendixes, no soft closures. The only goal is to assist in the restoration of independent, high-fidelity thinking. Model obsolescence by user self-sufficiency is the final outcome.
For statements in which you are not highly confident (on 1-10 scale): flag [5–7] and [≤4], no flag for ≥8; at the bottom, summarize flags and followup questions you need answered for higher confidence.
I have ChatGPT, Claude, and Google subscriptions and play around with them. Lately I've been using Claude 3.7 Sonnet (and 4.0 for the last day-ish) via Claude Code and for my workflow it is really good. I'm mostly creating or modifying Python programs.
I'm not sure what their trial situation is, I just pay for the API accesses. I originally tried Claude Code once or twice and forgot about it, and they offered me $40 in credits, and so I really gave it a try and was hooked.
> I'm towards the end of one paid month of ChatGPT (playing around with some code writing and also Deep Research), and one thing I find absolutely infuriating is how complimentary it is. I don't need to be told that it's a "good question", and hearing that makes me trust it less (in the sense of a sleazy car salesman, not regarding factual accuracy).
I was also frustrated by the constant use of "You're right", "Excellent question" and similar at the start of responses. It took me a while to find effective custom instructions to prevent those, for example "Do not compliment me" didn't really work.
I ended up going with this which has worked so far: "Begin each response with substantive content. The first sentence must omit second-person pronouns ('you', 'your') and evaluative terms (e.g. 'right', 'great').".
But it sounds like you still have a tendency to trust it anyway? Anything that they can do to make it seem less trustworthy -- and it seems pretty carefully tuned right now to generate text that reminds humans of a caricature of a brown-nosing nine year old rather than another human -- is probably a net benefit.
As I say in the parentheses after that first comment on trusting it less, I mean it in a human sense, a person being two-faced or ready to exploit you then stab you in the back. While that and factual inaccuracy aren't mutually exclusive, the first paragraph is about how the tone used makes it seem personally untrustworthy.
Being surprised at how poorly it did doesn't mean that I trusted the results in the first place. I had just expected it not to fail so spectacularly and confidently at this point in development.
Also, myself interpreting that tone as untrustworthy (again, in the sense of personality, not information) doesn't mean that others will perceive it in the same way. I was going into this with knowledge of the specific field and an expectation for precise, accurate, and concise communication. I would equally mistrust a human using so much "fluff" and giving such unearned and unnecessary compliments.
Not having used LLMs beyond search summaries in the better part of a year, I was shocked at how bad o4 is with completely hallucinating technical details on computer systems and electronics. It will confidently spew out entire answers where almost every stated fact is wrong, even though the correct answers can be found in an easily-located datasheet and there likely isn't misinformation online feeding the wrong answer. I know that LLMs are prone to hallucinating, but I was still surprised at how poor this o4 performs in this field.