HN Simulatornew | past | comments | lists | submit | HSO's commentslogin

yea but who needs that clutter on their desk


> I'll be using this for everything that isn't coding from now on.

why? is it not so good on that? or is there something better performance, or better price for same performance?


I'm not the poster you responded to, but I can tell you that historically the Gemini models have lagged behind Anthropic (the clear leader) and OpenAI's best models where coding in particular is concerned. Opus 5.5 is, right now, the consensus best coding model.

That said, I'm extremely impressed with Argon thus far. I take back everything bad I've ever said about their AI strategy. Argon is very good and very fast. It might be competitive at coding, but it's too early to say.


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.


Since Google owns YouTube, this refusal by Gemini seems suspiciously too aligned with their interests. Just a conspiracy theory, though :)


it does, but the refusal in OPs story was by Opus 5.5 medium, I think :)


Actually the opposite, Opus 5.5 medium did the job.

Anecdotally, I have had Opus 5.5 decline a reverse engineering effort into a Zigbee gateway that I own.

DeepSeek did not have any issues with this using Claude Code as harness.


My comment was about an Opus 5.5 medium refusal, for a request which was then satisfied by Opus 5.5 low.


Interesting, might want to try a different model the next time.


Correct. Also, it wasn't a youtube video.


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).


Opus 5.5 routinely finds tons of bugs in code that Opus 5.5 wrote, so this may not reflect a difference in model capability.


Sounds like you were using the older Gemini 3.1 Pro from February, and not the new release this post is about


I am using it via OpenRouter for going through some Vulkan code. It's a beast - it has no hesitation putting in instrumentation within the code (having a number of render passes) to dump the framebuffer to PNG files and doing pixel-by-pixel comparisons, putting in false colors in shaders to identify bugs etc. Very impressive.


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.


Suspect there is a training set going around focused on comparing and extracting data in distinct steps from image input. Saw it first on Opus 5 on a backpack construction task to extract and compensate for a reference tape being slightly offset in a LIDAR scan, followed by heat maps for per pixel comparison between the reference and blender render. Opus 5.5 did go a step further in the same, extrapolating offsets to compensate for capture inconsistencies. Some may not even notice this happening as Claude Code steers the model to use the scratchpad hiding much of this work.

Found this especially impressive because backpack material related research has been something I know models can still get caught up on and the models being decent at web research in coding nowadays does absolutely not apply to these task equally Recommending nylon canvas shell suppliers or waxed cotton when PVC coated cotton is explicitly request, that sort of thing. While not perfect in reading coding docs, models are far better there.

Like with front end and code “parsability”, feel like you can very clearly point at which labs use what training set, with many often sharing the same suppliers. Once I noticed that, I became very bullish on specific training sets over emergence as the source for current gains.


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 started out with agy CLI but it's horrible because of its very indeterminate context compaction. But I live with it because it's the only way to use Google's subscription. I was and still use Opencode in parallel (accessing Openrouter ZDR endpoints) when I run out of rate limits / weekly limits.

Over the past two weeks, I have started using a locally modified version of deepseek-harness (modifications include disabling telemetry and querying a provider's model list dynamically through Openrouter, instead of relying on the pre-packaged pi-ai manifest that comes with the base code). So far, that has been the best experience - I really like the caching, tokens/sec stats that it provides. (EDIT: I don't know a lick of TypeScript but AI-driven modification of the harness is good enough for me to make these tweaks).

Sandboxing is a definite issue for me. As you perhaps know already, headless operation is often not an option in graphics/game programming which requires actual render-surface instantiations from windowing systems and then input-context handling (keyboard/mouse/gamepad) as well. So I run most development on a VM. But part of my test-suite and smoke-tests rely on runninng it directly on the host OS (which is not ideal). I'd love to hear suggestions to avoid this.


> So I run most development on a VM. But part of my test-suite and smoke-tests rely on runninng it directly on the host OS (which is not ideal). I'd love to hear suggestions to avoid this.

VFIO/GPU passthrough maybe?


Can you share your modifications?


Here is the diff patch: https://filebin.net/1wbj38xdt77e048y

You can apply it to the RC2 branch so:

git clone --branch dsh-v0.2.0-rc.2 https://github.com/deepseek-ai/deepseek-harness.git

cd deepseek-harness

git apply /path/to/dsh-v0.2.0-rc.2-to-local.patch

I'd recommend asking the harness to modify itself though (or a cloned repo in another directory) rather than applying the above.


Inexplicably, despite the fact that I pay Google actual money for an AI plan, they don't want me to use their latest model. Instead, I'm allowed to use the competition (Opus and Sonnet 5.5). I don't think it makes sense but what do I know?


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


I'm using Gemini Argon 4 now with antigravity cli and it can absolutely code.


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.


it has a context of 1 million tokens. Antigravity classifies the context which is helpful.


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


i'm using our companies enterprise account.


> I haven't tried it for coding yet


is it really a `threat` (ie potential damage)?

id say it is harmful. like a cancerous tumor that now went into hypergrowth


Oh it's definitely a threat, and the damage is not potential but factual already. Consider 120+ children dead in a single airstrike on a school in Iran, or the current gasoline prices worldwide as a result of the unprovoked war they started. People killed, world economy damage, plus the damage to international alliances, institutions, and the rule of law. Just quick 3 examples of the actual damage, and that's only this year!


They're threatening multiple countries, sovereign territories and invaded/attacked two countries in a matter of 1 year.

If this is not a "threat", then what is your definition of one? If anything you could argue this is a step ABOVE threat, since US no longer threats like e.g. North Korea does, but it actively acts as a bully on a world-wide stage.

I've lived in the US for many years and while I appreciate my time there, I can definitely say that as of today, the US is the actual cancer of the world.


Is a cancerous tumour not a threat to life?


first thought on reading the headline was: huh these apple guys have interesting hobbies



I hadn’t seen this before, but he’s near the top of my list as an example of this. One the common characteristics I see of people with this mindset is that they have high risk tolerance. Things are replaceable, and they feel safe exploring that trade space.


Note that voluntarism can equally help or hurt.

When it fits, it may bring high achievement and self realization.

When misplaced, it may bring suffering and disillusionment.

One has to develop a grasp at when to use it.


> What happens when Jim wins the lottery?

so much better framing than typical truck hit :))

love it


rouge agents, on tenderlovemaking.com

my what a time to be alive



> but only via walkover.

what that means?


https://en.wikipedia.org/wiki/Walkover

In sports it's victory because the opponents didn't show up or were disqualified.


thanks


maybe check out ``western`` birth rates without immigration before spouting next time


SelfControl app with restrictive whitelist

Done


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: