Comment by svara

Many times you lack the context or words, but after it gave them to you, you can look up papers and figure out if it matches. Same as you do with human doctors to decide if you need a second opinion.

You don’t. But its shiny and pretty.

If you have a solid self assessment of what you know, you can consider when information is supported by what you know. For the parts that aren't, you consider how critical they are, and identify the area that needs a deeper dive, where you either link it back to other areas you have confidence in your own knowledge or work to expand your own knowledge (using other resources). Then cross check knowledge. The cheap way you can do easily is to cross check between AIs/harnesses, because hallucinations happen randomly, so two different models in two different harnesses having the same hallucination is extremely rare. The more expensive option, which should be used when the information really matters, is building your own knowledge. Have the AI help guide you to resources, but not be the resource. While using non-AI resources, check you knowledge against them and the AI. Test yourself with classical resources where it really matters.

Part of it is using good judgment. Is the AI's claim reasonable if it came from another person? If some random person gave you a 2 page paper proving P=NP, would you even spend time to look at it, or would you simply toss it without caring to understand what error they made. Much like how scientists (and even the patent office) simply refuse to entertain any perpetual motion machines. Maybe if an expert in the field proposed it, and even that would depend upon how ("Hey, I found a source of free energy!" vs "Hey, I'm working through these equations and the energy term isn't balancing, can you help me find what energy source I'm missing?").

This does pose a problem. Those who are the best at understanding the limits of their knowledge and at teaching themselves need the AI's help the least but are in the position to be able to use AI with the best chance of not being misled. Those who lack these skills and would benefit the most from a personal educator, thus receving the biggest benefit in theory, are the ones most likely to fall victim to the errors made by the AI.

Sometimes you can go to the websites of your country's health care system, look up what it said, read and compare.

I mean, in this case it linked me to many sources, including the manual for the OCT machine used. One thing that even my ophthalmologist might not know, buried in the PDF manual, is that the sample size only includes 5 people under the age of 35 (skewing my "1st percentile" results more aggressively).

But you're right that you can't be 100% certain. Isn't that true for human-to-human explanations too?

How do you know that for a web site? You have to research and cross check, and talk to a real doctor.

Easy. Just feed the results to a second frontier model to verify. /s

Ask a doctor?

Absolutely. As one of my physician friends told me: “half the time, the best plan is, ‘We'll have to wait and see.’”

But, as a patient, it's hard to find comfort in that. I think that might be what drives the craziness in “non-traditional” approaches to treating disease. Could it be that people using fruititarian diets and essential oils for cancer are doing so because they don’t understand enough to bear a “wait and see” situation?

Argon explained the problem to me in such depth that I could be content with my basic treatment plan. ChatGPT went way off the deep end, suggesting things like high-dose niacinamide treatment (which is admittedly being evaluated in clinical trials, but comes with a host of other side effects).

I have no idea how I’d have even started on a project like this in 2020… certainly not by writing raw WebGL — ha!

It is a very efficient model, which I really appreciate. It can definitely feel a little slow. I tend to not hang around for it to do its thing, but for orchestrating and taking somewhat vaguely defined coding goals it is pretty amazing.

gemini.google.com with a $20/month Pro membership.

It's available via OpenRouter

Opus 5.5 medium is a real sweet spot for many many things. But. I got an unexpected refusal (for help creating a browser console script to convert a web-based streaming video to an offline-ready .mp4), which Opus 5.5 low happily provided.

I completely agree; I was really surprised to find that Claude Code Opus 5.5 is significantly better. I had spent quite a bit of time using Gemini Pro for coding tasks, but when I revisited the code analysis using Opus 5.5, it revealed quite a few shortcomings in Gemini's understanding... I code using Python, which is considered the best language for writing code via LLMs (I am referring to linguistic entropy).

That’s something Opus can also do. Perhaps by coincidence I also recently debugged shader bugs where Opus dumped the resulting render to PNGs and then using Python PIL to do comparisons. It purposefully added false colors too.

Out of curiosity, which harness do you use for this kind of task, and how do you sandbox it? I used Aider before, and consider switching to a more recent tool.

I think the rollout was phased. I couldn't see Argon in Antigravity on my personal AI Pro account until late last night.

When does it auto compact? Is it at 250k tokens as for gemini-3.8-flash? If it's more generous I might consider upgrading to the ultra plan.

do you have ultra plan? it says regular sub doesn't have it.

Coding is probably one of the worst value propositions, in terms of consuming more tokens per subscription dollar. Doing well in coding might even hurt Google's revenues: it would cannibalize some proportion of Anthropic's user base, which Anthropic serves by... renting Google's infra.

There were rumors that the reason Gemini was delayed was because it was too bad at coding.

In my personal testing, Argon is exceptional at writing tasks. After a few simple eval loops of you correcting things into your own voice you can have it sound almost exactly like you.

Lately, I've been having a lot of Socratic conversations with agents to understand these kind of topics, this helps me a ton, thank you so much!

Kinda odd there's no mention of room humidity.....

Generating pelicans on bicycles most likely

I think there's definitely some quantization or nerfing happening post-release -- I definitely noticed that with Gemini Flash 3.7, it was super fast and accurate at the start and a few weeks later seemed to run in circles and overthink even a "what are you doing" message, all while doing almost identical work. I find it weird that we're so far into the LLM era and the post-launch degradation is still something of a conspiracy theory.

What would that prove if we are testing whether they "are just secretly hamstringing the previous models" as GP claimed?