Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all.
agreed. when using local models, they did send your prompts to openai with 30 day retention to make the titles, silently.
their recent changes to the privacy policy broke their promise of zero data retention. specifically, they offered chatgpt luna under a zero data retention privacy policy. luna was later shown to be 30 days retention.
their privacy policy has never guaranteed your prompts will not be logged and when asked they have failed to revise it.
when challenged about sending data to openrouter without listing it as a 3rd party processor they offered a dismissive response. the same with running prompts through cloudflare. seems trivial, but signifies general disinterest in security.
by default if you run the harness outside your config file by accident, it will automatically run silently with a free model that sends your prompts and local data to an endpoint with training enabled. on top of that it used to dump all the prompts sent to free models into an s3 bucket, the feature was literally called 'datadumper' in the source.
Plus 100 to this. Of all the harnesses I find it to be the worst. IMO training should always require opt in and the way they continue to run their business/framework is shady.
Yeah, the combo of hidden telemetry and other shenanigans along with general code bloat and other tradeoffs among the handful of available OSS harness options are what convinced us it was worth writing a new harness from scratch.
Probably less of an issue but I always disliked with their paid plan/credits that they made I nonobvious that some of the Chinese models train off of your usage. It may have changed now but they would show all these great models you could use, somewhere have a bullet that everything is private adobe have an asterisk next to a handful of those models (including their own). I am sure some cost sensitive folks are ok with that but I disliked how there was not an easy way to tell and it was opt in automatically if you used those models.
You have to enable explicit opt-in to use models hosted in China now. This changed in July +/- 2w. I already used DeepSeek, but it was nice to make that explicit for people that were concerned.
OpenCode does not leak "all your data". Author did not "feign ignorance" and there is no "issue to be fixed."
Title generation is handled by the small_model setting in the config. If you have that configured to use a local LLM, then that is where the your prompt will be sent to generate a session title.
Actually I have been quite curious about this. I have a Qwen 3.5 800M model kept in memory just for this type of processing, and I set my small_model setting to use it. But it isn’t receiving any requests and somehow the titles are still generated…
The reason to run local models is not for coding mostly it's for learning how to deploy models and tinker with self hosting. It's also for massively crunching data 24/7. Imaging having an agent analyzing constinous log streams etc .. that could be a usescse where even deepseek could add up cost.
One thing I realized is just how much offline local models can hurt mass data collection.
For example, I needed to write an invitation letter for immigration control for a relative visiting me. Previously I would have used a search engine for a template. Today I fire up my local qwen 3.5-9b for this kind of stuff and feed it all the private data I need.
Unfortunately it is unlikely the average user will known how to avoid this data collection. Even if the LLM is local you are likely feeding the prompts to remote servers if you harness/chat-interface is not properly vetted.
I'd really rather just pay Deepseek directly. Why wouldn't I want to support the company that trained the model?
It isn't even really worth the (minimal) ops to stand up rented MI300Xs to sell excess capacity to them even if it was minimally profitable, when I tried I was content to give API keys to friends to beat on it.
That's only true if the value of keeping your data and code private is zero. And in that case, Anthropic and OpenAI subscription plans may be even cheaper per day.
I think it's back to 2X usage, meaning it's cheaper token-burn than usual to use. Which is lovely.
OpenCode Go has been so nice to have. I love having access to DeepSeek, Qwen and MiniMax M3 when doing design work, to see what different models cook up. I've been very surprised with MiniMax M3, not as a particularly good architect, but at it's very good ability to state the problem elegantly & to frame the different decision points very well. That's been a fun ongoing surprise.
Since the announcement of DeepSeek price hike, I have been using MiniMax M3 and I am really surprised by the quality this model spits out. Subjectively speaking, the bullshit MM3M produces is waaay less than DS0731.
Could it be a result of less hallucinations than DS0731?
https://artificialanalysis.ai/evaluations/omniscience#aa-omn...
Maybe hallucination is good for prototyping and creative work, but maintaining and debugging code might be better done by a boring model?
but DS prices havent increased yet... in fact, opencode go is offering an extra 2x bonus on DS Flash right now. Why switch before anything has changed?
I have a stack of ten or so 3090s sitting in boxes, but it's not worth the hassle to use them. You can easily run models as cheap as water in the cloud.
Sitting around 15 minutes for local Minimax is stupid when you're trying to be productive. You can spin up parallel job instances and multitask in the cloud.
If you want freedom, build open source cloud infra.
You rent your ISP line. Why isn't renting GPU compute seen the same way? You still have compete ownership over your stack, you're just letting someone else deal with the capital outlay and headache.
The value prop really depends on what you're doing.
If you're just vibe coding with giant frontier models, yes, the value will be worse. Especially now, where GPU prices have spiked another 20% last month.
For some tasks where owning the setup and full kv cache matters, the payoff calculation is ridiculously in favor of running your own deployment.
For instance for some batch classifications jobs where the prefix cache hit rate will be >95%.
The calculus also changes if you just use AI as a light tool while coding and don't need the giant models; qwen3 27B runs at 80TPS on a 5090 properly deployed.
> You rent your ISP line. Why isn't renting GPU compute seen the same way?
Is it mostly seen the same way. What is unacceptable is removing the freedom (which you mentioned) of people who prefer to run models locally.
Just as people have the right to tinker at home with DIY and electronics, fully knowing they won't compete with the latest ASML machine, people are free to use open-weight models at home.
BTW Minimax H3 running local can generate amazing short vids quite fast: about 50 seconds to generate a 7 seconds vids on a 4090 (depending on the settings). I've got a friend who spams my Telegram daily with such (no censorship and NSFW btw) vids.
I don't run local but I'll defend the rights of people who want the freedom to do so and I won't look down at them from my high-horse talking about "electricity" and "productivity".
Beware of the author of tweet, who happens to be author of OpenCode - OpenCode will leak all your data to themselves and to shady 3rd parties. Author feigned ignorance and never fixed the issue. OpenCode among other harnesses is the shadiest of all.
https://github.com/anomalyco/opencode/issues/10416
agreed. when using local models, they did send your prompts to openai with 30 day retention to make the titles, silently.
their recent changes to the privacy policy broke their promise of zero data retention. specifically, they offered chatgpt luna under a zero data retention privacy policy. luna was later shown to be 30 days retention.
their privacy policy has never guaranteed your prompts will not be logged and when asked they have failed to revise it.
when challenged about sending data to openrouter without listing it as a 3rd party processor they offered a dismissive response. the same with running prompts through cloudflare. seems trivial, but signifies general disinterest in security.
by default if you run the harness outside your config file by accident, it will automatically run silently with a free model that sends your prompts and local data to an endpoint with training enabled. on top of that it used to dump all the prompts sent to free models into an s3 bucket, the feature was literally called 'datadumper' in the source.
Plus 100 to this. Of all the harnesses I find it to be the worst. IMO training should always require opt in and the way they continue to run their business/framework is shady.
Yeah, the combo of hidden telemetry and other shenanigans along with general code bloat and other tradeoffs among the handful of available OSS harness options are what convinced us it was worth writing a new harness from scratch.
Probably less of an issue but I always disliked with their paid plan/credits that they made I nonobvious that some of the Chinese models train off of your usage. It may have changed now but they would show all these great models you could use, somewhere have a bullet that everything is private adobe have an asterisk next to a handful of those models (including their own). I am sure some cost sensitive folks are ok with that but I disliked how there was not an easy way to tell and it was opt in automatically if you used those models.
You have to enable explicit opt-in to use models hosted in China now. This changed in July +/- 2w. I already used DeepSeek, but it was nice to make that explicit for people that were concerned.
Always believe accounts created less than an hour ago.
It's not even possible to delete one's account!
[delayed]
I guess that's why they called OpenCode
I like how everything you said is false.
OpenCode does not leak "all your data". Author did not "feign ignorance" and there is no "issue to be fixed."
Title generation is handled by the small_model setting in the config. If you have that configured to use a local LLM, then that is where the your prompt will be sent to generate a session title.
Actually I have been quite curious about this. I have a Qwen 3.5 800M model kept in memory just for this type of processing, and I set my small_model setting to use it. But it isn’t receiving any requests and somehow the titles are still generated…
+1, but I think the documentation surrounding this should be a bit better. I didn‘t know they did this until I read that comment
The account is 47 minutes old
Thats not that big of an issue. Seeing a lot of accusations against opencode, regarding all kind of things, here on HN lately.
Anything of substance besides shallow dismissal and (anti)appeal to masses?
The reason to run local models is not for coding mostly it's for learning how to deploy models and tinker with self hosting. It's also for massively crunching data 24/7. Imaging having an agent analyzing constinous log streams etc .. that could be a usescse where even deepseek could add up cost.
Also privacy and offline capabilities.
One thing I realized is just how much offline local models can hurt mass data collection.
For example, I needed to write an invitation letter for immigration control for a relative visiting me. Previously I would have used a search engine for a template. Today I fire up my local qwen 3.5-9b for this kind of stuff and feed it all the private data I need.
Unfortunately it is unlikely the average user will known how to avoid this data collection. Even if the LLM is local you are likely feeding the prompts to remote servers if you harness/chat-interface is not properly vetted.
I'd really rather just pay Deepseek directly. Why wouldn't I want to support the company that trained the model?
It isn't even really worth the (minimal) ops to stand up rented MI300Xs to sell excess capacity to them even if it was minimally profitable, when I tried I was content to give API keys to friends to beat on it.
That's only true if the value of keeping your data and code private is zero. And in that case, Anthropic and OpenAI subscription plans may be even cheaper per day.
That's almost half way to their stated 6X usage goal! Just from DeepSeek.
> With Go, you pay $10/month and we aim to give you 6x that in usage.
For most models, we make this work through bulk discounts and reserved GPU capacity. We then pass those savings on to you through the 6x multiplier.
https://opencode.ai/docs/go/#why-some-models-have-lower-usag...
I think it's back to 2X usage, meaning it's cheaper token-burn than usual to use. Which is lovely.
OpenCode Go has been so nice to have. I love having access to DeepSeek, Qwen and MiniMax M3 when doing design work, to see what different models cook up. I've been very surprised with MiniMax M3, not as a particularly good architect, but at it's very good ability to state the problem elegantly & to frame the different decision points very well. That's been a fun ongoing surprise.
Since the announcement of DeepSeek price hike, I have been using MiniMax M3 and I am really surprised by the quality this model spits out. Subjectively speaking, the bullshit MM3M produces is waaay less than DS0731. Could it be a result of less hallucinations than DS0731? https://artificialanalysis.ai/evaluations/omniscience#aa-omn...
Maybe hallucination is good for prototyping and creative work, but maintaining and debugging code might be better done by a boring model?
but DS prices havent increased yet... in fact, opencode go is offering an extra 2x bonus on DS Flash right now. Why switch before anything has changed?
Don’t forgot a number of models they have offered to you will train on your data
Deepseek will run fine on a single m5 max, cutting that 24 years in half.
also worth remembering API price includes power, just dividing price of the hardware by usage doesn't
The post is also misleading because the m5 max 128 gb costs a lot and you can only run DS4 flash quantized, thus not a 1:1 comparison.
Cloud > Local
I have a stack of ten or so 3090s sitting in boxes, but it's not worth the hassle to use them. You can easily run models as cheap as water in the cloud.
Sitting around 15 minutes for local Minimax is stupid when you're trying to be productive. You can spin up parallel job instances and multitask in the cloud.
If you want freedom, build open source cloud infra.
You rent your ISP line. Why isn't renting GPU compute seen the same way? You still have compete ownership over your stack, you're just letting someone else deal with the capital outlay and headache.
Why are you hoarding the 3090s T.T They've jumped from $700 to almost double on eBay.
The value prop really depends on what you're doing.
If you're just vibe coding with giant frontier models, yes, the value will be worse. Especially now, where GPU prices have spiked another 20% last month.
For some tasks where owning the setup and full kv cache matters, the payoff calculation is ridiculously in favor of running your own deployment.
For instance for some batch classifications jobs where the prefix cache hit rate will be >95%.
The calculus also changes if you just use AI as a light tool while coding and don't need the giant models; qwen3 27B runs at 80TPS on a 5090 properly deployed.
Why not rent those out on vast.ai and make a little money each month?
Why do you have ten or so 3090s sitting in boxes?
I mean obviously it's worth it just so you can flex on HN. But curious whether there was any other reason? Retired scalper?
Do you really keep ten cards in boxes just to brag on Hacker News? Geez, our industry has gotten pathetic.
> You rent your ISP line. Why isn't renting GPU compute seen the same way?
Is it mostly seen the same way. What is unacceptable is removing the freedom (which you mentioned) of people who prefer to run models locally.
Just as people have the right to tinker at home with DIY and electronics, fully knowing they won't compete with the latest ASML machine, people are free to use open-weight models at home.
BTW Minimax H3 running local can generate amazing short vids quite fast: about 50 seconds to generate a 7 seconds vids on a 4090 (depending on the settings). I've got a friend who spams my Telegram daily with such (no censorship and NSFW btw) vids.
I don't run local but I'll defend the rights of people who want the freedom to do so and I won't look down at them from my high-horse talking about "electricity" and "productivity".