News for hackers. Stuff that matters.
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @09:48AM (#39591134)
Just added Claude 3 to Chat at https://double.bot if anyone wants to try it for coding. Free for now and will push Claude 3 for autocomplete later this afternoon.

From my early tests this seems like the first API alternative to GPT4. Huge!

Re:Claude 3 model family by gkfasdfasdf on Monday March 04, 2024 @12:15PM (#39592910)
How do you guys compare to codium [0]? Also, any plans to support vim/neovim integration (codium has pretty good support in place [1]). Thanks.

[0] - https://www.codium.ai

[1] - https://github.com/Exafunction/codeium.vim

Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @12:23PM (#39593026)
I think the tldr would be that they have more products (for example, their agent to write git commit messages). In the products we do have (autocomplete, chat), we spend a lot of time to get the details right. For example for autocomplete:

* we always close any brackets opened by autocomplete (and never extra brackets, which is the most annoying thing about github copilot)

* we automatically add import statements for libraries that autocomplete used

* mid-line completions

* we turn off autocomplete when you're writing a comment to avoid disrupting your train of thought

You can read more about these small details here: https://docs.double.bot/copilot

As you noted we don't have a vim integration yet, but it is on our roadmap!

Re:Claude 3 model family by CMS_Flash on Monday March 04, 2024 @06:42PM (#39597626)
Do note that Codium and Codeium are two completely separate companies. They work in related fields but have very different approaches.
Re:Claude 3 model family by gkfasdfasdf on Wednesday March 06, 2024 @07:58AM (#39615461)
Wow you are right. That is confusing! I was asking about Codeium (with an e) but I linked the wrong one in my post. The vim plugin link is correct though.
Re:Claude 3 model family by addandsubtract on Monday March 04, 2024 @09:59AM (#39591256)
So double is like copilot, but free? What's the catch?
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @10:13AM (#39591399)
No catch. We're pretty early tbh so mostly looking to get some early power users and make the product great before doing a big launch. It's been popular with yc founders in the latest batches thus far but we haven't really shared publicly. We'll charge when we launch. If you try it now, I hope you'll share anything you liked and didn't like with us!
Re:Claude 3 model family by yangcheng on Tuesday March 05, 2024 @05:22AM (#39601544)
First time saw it, would love to try, do I need to uninstall co-pilot plugin to use double?
Re:Claude 3 model family by behnamoh on Monday March 04, 2024 @10:13AM (#39591402)
I guess your data is the catch.
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @10:15AM (#39591428)
We don't store or train on your data. You can see more details on our privacy policy here https://docs.double.bot/legal/privacy
Re:Claude 3 model family by parkersweb on Monday March 04, 2024 @01:11PM (#39593795)
Interesting - I had this exact question and tried the search on the website to find the answer with no result :D

Would be great to have an FAQ for this type of common question

Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @01:15PM (#39593843)
Thanks for the feedback – what search terms did you use? Let me make sure those keywords are on the page :P
Re:Claude 3 model family by ShamelessC on Monday March 04, 2024 @11:54AM (#39592617)
Probably not data so much as growth numbers to appease investors. Such offerings typically don’t last forever. Might as well take advantage while it lasts.
Re:Claude 3 model family by brainless on Monday March 04, 2024 @10:22AM (#39591502)
Hey Wesley, I just checked Double. Do you plan to support open source models hosted locally or on a cloud instance? Asking out of curiosity as I am building a product in the same space and have had a few people ask this. I guess since Double is an extension in IDEs, it can connect to AI models running anywhere.
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @10:55AM (#39591889)
it's an interesting idea. We asked our users this as well but at least for those we talked to, running their own model wasn't a big priority. What actually mattered to them is being able to try different (but high performance) models, privacy (their code not being trained on), and latency. We have some optimizations around time-to-first-token latency that would be difficult to do if we didn't have information about the model and their servers.
Re:Claude 3 model family by brainless on Monday March 04, 2024 @11:57AM (#39592657)
I see. Thanks Wesley for sharing and great to know it is not a priority. Also, the Mistral situation kinda makes me feel that big corps will want to host models.

Although, I feel Apple will break this trend and bring models to their chips rather than run them on the cloud. "Privacy first" will simply be a selling point for them but generally speaking cloud is not a big sell for them.

I am not at the level to do much optimizations, plus my product is a little more generic. To get to MVP, prompt engineering will probably be my sole focus.

Re:Claude 3 model family by behnamoh on Monday March 04, 2024 @10:48AM (#39591805)
To be clear: Is this Claude 3 Opus or the Sonnet model?
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @10:50AM (#39591823)
opus. only the best!
Re:Claude 3 model family by behnamoh on Monday March 04, 2024 @10:56AM (#39591893)
Awesome! I like the inline completions.

But could you let the users choose their keyboard shortcuts before setting the default ones?

Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @11:33AM (#39592323)
Thanks for the feedback. I was actually reworking the default shortcuts and the onboarding process when I got pre-empted by claude. I was planning to change the main actions to alt-j, alt-k to minimize conflicts.

Are you asking because it conflicts with an existing shortcut on your setup? Or another reason?

Re:Claude 3 model family by behnamoh on Monday March 04, 2024 @11:47AM (#39592506)
Yes, it conflicts with some of my other shortcuts, but more generally, I think it'd be better to have consistent shortcuts, like CMD-CTRL-i for inline completion, CMD-CTRL-c for chat, etc.
Re:Claude 3 model family by trenchgun on Monday March 04, 2024 @11:50AM (#39592556)
How do I change GPT4 to Claude 3 in double.bot?
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @12:02PM (#39592731)
It's default to claude 3 right now so I could get it out quick, but working on a toggle for the front-end now to switch between the two.
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @09:43PM (#39598867)
for future readers, the setting is now shipped in >v0.49. The default is now back to GPT-4 as it has lower latency but you can manually change it to Claude 3 in settings if you wish to try out Anthropic's new model.
Re:Claude 3 model family by firestar464 on Monday March 04, 2024 @11:39PM (#39599510)
It seems that a lot of the techies here have found it easy to find settings, but I seem to have trouble with that. Would you mind assisting me?
Re:Claude 3 model family by trenchgun on Tuesday March 05, 2024 @02:35AM (#39600411)
It's in the same place as settings are for any installed VSCode extension.
Re:Claude 3 model family by firestar464 on Tuesday March 05, 2024 @03:20AM (#39600673)
Yeah, I eventually found it. Thanks anyway :)

I noticed it might actually be a little more censored than the lmsys version. Lmsys seems more fine with roleplaying, while the one on Double doesn't really like it

Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @10:14AM (#39591406)
Seems like the API is less reliable than GPT-4 so far, but I guess it makes sense for the endpoint to be popular at launch!
Re:Claude 3 model family by 098799 on Monday March 04, 2024 @10:42AM (#39591746)
Emacs implementation when? ;)
Re:Claude 3 model family by behnamoh on Monday March 04, 2024 @12:04PM (#39592746)
If you use Emacs you're expected to know your way around programming and not need copilots :)
Re:Claude 3 model family by trenchgun on Tuesday March 05, 2024 @02:37AM (#39600423)
You have not checked GPTel then. It is super useful! Emacs really makes a good pairing with LLMs.
Re:Claude 3 model family by BeetleB on Monday March 04, 2024 @11:00AM (#39591929)
I just checked - surprisingly I cannot find any Emacs AI implementation that supports Claude's API.
Re:Claude 3 model family by karthink on Monday March 04, 2024 @01:32PM (#39594070)
Just added it to gptel.
Re:Claude 3 model family by karthink on Monday March 04, 2024 @01:32PM (#39594064)
Just added it to gptel. (No image support though, it's a text-only LLM client.)
Re:Claude 3 model family by 098799 on Monday March 04, 2024 @02:15PM (#39594662)
Thank you for working on gptel, it's an excellent package. I'm still using the copilot more because of the pure speed (competing with company mode/LSP), but I never use it if it suggests more than one line. The quality is just not there. But having access to gpt4 from gptel has been very useful. Can't wait to play around with Claude 3.
Re:Claude 3 model family by trenchgun on Tuesday March 05, 2024 @02:36AM (#39600415)
Wow, this was fast. Excellent!
Re:Claude 3 model family by benreesman on Sunday March 10, 2024 @12:42AM (#39656981)
Fantastic work! I'm a huge fan of `gptel` and hope to contribute when I can.

Thank you again for the great tool.

Re:Claude 3 model family by trenchgun on Monday March 04, 2024 @10:25AM (#39591537)
Very nice!
Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @12:51PM (#39593496)
more early impressions on performance: besides the endpoint erroring out at a higher rate than openai, time-to-first-token is also much slower :(

p50: 2.14s p95: 3.02s

And these aren't super long prompts either. vs gpt4 ttft:

p50: 0.63s p95: 1.47s

Re:Claude 3 model family by Intralexical on Monday March 04, 2024 @06:52PM (#39597692)
FYI That website doesn't work on QtWebEngine5.

(Chromium 87.0.4280.144 (Jan. 2021), plus security patches up to 119.0.6045.160 (Nov. 2023).)

Re:Claude 3 model family by wesleyyue on Monday March 04, 2024 @08:42PM (#39598459)
Thank you for the report! We're using Mintlify for the docs (which that URL links to). Let me report it upstream to see if they can fix.
Re:Claude 3 model family by p1esk on Monday March 04, 2024 @10:38PM (#39599149)
seems like the first API alternative to GPT4

What about Ultra?

Re:Claude 3 model family by machdiamonds on Monday March 04, 2024 @10:49PM (#39599205)
Hi, what differentiates double from Cursor?
Re:Claude 3 model family by meelgaurav7 on Monday March 11, 2024 @11:48PM (#39676006)
Explain the following article in smaller points and in very simple words and in 750 words for better understanding.Huawei Chip Breakthrough Used Tech From Two US Gear Suppliers

SMIC used Applied Materials and Lam equipment to make 7nm chip

US wants to further limit China’s access to foreign chip tech

Bloomberg has learned that Huawei and its partner SMIC relied on gear from Applied Materials Lam Researchto produce an advanced chip.

Huawei Technologies Co. and its partner Semiconductor Manufacturing International Corp. relied on US technology to produce an advanced chip in China last year, according to people with knowledge of the matter.

Shanghai-based SMIC used gear from California-based Applied Materials Inc. and Lam Research Corp. to manufacture an advanced 7-nanometer chip for Huawei in 2023, the people said, asking not to be named as the details are not public.

The previously unreported information suggests that China still cannot entirely replace certain foreign components and equipment required for cutting-edge products like semiconductors. The country has made technological self-sufficiency a national priority and Huawei’s efforts to advance domestic chip design and manufacturing have received the backing of Beijing.

Representatives of SMIC, Huawei and Lam did not respond to requests for comment. Applied Materials and the US Commerce Department’s Bureau of Industry and Security, which is responsible for implementing export controls, declined to comment.

Lauded in China as a major leap in indigenous semiconductor fabrication, last year’s SMIC-made processor powered Huawei’s Mate 60 Pro and a wave of patriotic smartphone-buying in the Asian country. The chip is still generations behind the top components from global firms, but ahead of where the US hoped to stop China’s advance.

The machinery used to make it, however, still had foreign sources including technology from Dutch maker ASML Holding NV as well as the gear from Lam and Applied Materials. Bloomberg News reported in October that SMIC had used equipment from ASML for the chip breakthrough.

Leading Chinese chip equipment suppliers including Advanced Micro-Fabrication Equipment Inc. and Naura Technology Group Co. have been trying to catch up with their American peers, but their offerings are still not as comprehensive or sophisticated. China’s top lithography system developer Shanghai Micro Electronics Equipment Group Co. still lags a few generations behind what industry leader ASML is capable of.

SMIC obtained the American machinery before the US banned such sales to China in October 2022, some of the people said. Both firms were among the American suppliers that began pulling their staff from China after those rules went into effect and prohibited US engineers from servicing some machines in the Asian country. ASML also told American employees to stop working with Chinese customers in response to the US curbs, but Dutch and Japanese engineers are still able to service many machines in China — much to the chagrin of their American rivals.

Companies are now prohibited from selling cutting-edge, US-origin technology to either SMIC or Shenzhen-based Huawei. Both tech firms have been blacklisted by the US for alleged links to the Chinese military, while Washington has been tightening China’s overall access to chipmaking equipment and advanced semiconductors.

Those trade curbs pushed Huawei and SMIC to pursue avenues for building a domestic chip supply chain, and the Mate 60 Pro marked a surprising advance in that effort.

After Huawei released the new phone, Washington launched a probe into its processor and US Commerce Secretary Gina Raimondo vowed the “strongest possible” actions to ensure national security. Meanwhile, Republican lawmakers have called for the Biden administration to completely cut off Huawei and SMIC’s access to US technology.

Department of Commerce officials have said they haven’t seen evidence that SMIC can make the 7nm chips “at scale,” a point echoed by ASML’s Chief Executive Officer Peter Wennink.

If SMIC wants to advance its technology without ASML’s state-of-the-art extreme ultraviolet lithography systems, the Chinese chipmaker will not be able to produce chips at a commercially meaningful volume due to technical challenges, Wennink told Bloomberg News in late January.

“The yield is going to kill you. You’re not going to get the number of chips that you need to have high volume chip production,” he said. ASML has not been able to sell its EUV systems to China as the Dutch government has not issued a license allowing those exports.

The US, meanwhile, is pressing allies including the Netherlands, Germany, South Korea and Japan to further tighten restrictions on China’s access to semiconductor technology. That effort is proving controversial and meeting resistance in some countries, as it imposes limits on trade at a time that Chinese businesses are investing in equipment and computational power to compete in the artificial intelligence race.

Huawei may be China’s most promising candidate to develop AI chips to compete with the US. Industry leader Nvidia Corp.’s CEO, Jensen Huang, in December called the Shenzhen firm a “formidable” rival.

Re:Claude 3 model family by meelgaurav7 on Monday March 11, 2024 @11:48PM (#39676011)
Huawei Chip Breakthrough Used Tech From Two US Gear Suppliers

SMIC used Applied Materials and Lam equipment to make 7nm chip

US wants to further limit China’s access to foreign chip tech

Bloomberg has learned that Huawei and its partner SMIC relied on gear from Applied Materials Lam Researchto produce an advanced chip.

Huawei Technologies Co. and its partner Semiconductor Manufacturing International Corp. relied on US technology to produce an advanced chip in China last year, according to people with knowledge of the matter.

Shanghai-based SMIC used gear from California-based Applied Materials Inc. and Lam Research Corp. to manufacture an advanced 7-nanometer chip for Huawei in 2023, the people said, asking not to be named as the details are not public.

The previously unreported information suggests that China still cannot entirely replace certain foreign components and equipment required for cutting-edge products like semiconductors. The country has made technological self-sufficiency a national priority and Huawei’s efforts to advance domestic chip design and manufacturing have received the backing of Beijing.

Representatives of SMIC, Huawei and Lam did not respond to requests for comment. Applied Materials and the US Commerce Department’s Bureau of Industry and Security, which is responsible for implementing export controls, declined to comment.

Lauded in China as a major leap in indigenous semiconductor fabrication, last year’s SMIC-made processor powered Huawei’s Mate 60 Pro and a wave of patriotic smartphone-buying in the Asian country. The chip is still generations behind the top components from global firms, but ahead of where the US hoped to stop China’s advance.

The machinery used to make it, however, still had foreign sources including technology from Dutch maker ASML Holding NV as well as the gear from Lam and Applied Materials. Bloomberg News reported in October that SMIC had used equipment from ASML for the chip breakthrough.

Leading Chinese chip equipment suppliers including Advanced Micro-Fabrication Equipment Inc. and Naura Technology Group Co. have been trying to catch up with their American peers, but their offerings are still not as comprehensive or sophisticated. China’s top lithography system developer Shanghai Micro Electronics Equipment Group Co. still lags a few generations behind what industry leader ASML is capable of.

SMIC obtained the American machinery before the US banned such sales to China in October 2022, some of the people said. Both firms were among the American suppliers that began pulling their staff from China after those rules went into effect and prohibited US engineers from servicing some machines in the Asian country. ASML also told American employees to stop working with Chinese customers in response to the US curbs, but Dutch and Japanese engineers are still able to service many machines in China — much to the chagrin of their American rivals.

Companies are now prohibited from selling cutting-edge, US-origin technology to either SMIC or Shenzhen-based Huawei. Both tech firms have been blacklisted by the US for alleged links to the Chinese military, while Washington has been tightening China’s overall access to chipmaking equipment and advanced semiconductors.

Those trade curbs pushed Huawei and SMIC to pursue avenues for building a domestic chip supply chain, and the Mate 60 Pro marked a surprising advance in that effort.

After Huawei released the new phone, Washington launched a probe into its processor and US Commerce Secretary Gina Raimondo vowed the “strongest possible” actions to ensure national security. Meanwhile, Republican lawmakers have called for the Biden administration to completely cut off Huawei and SMIC’s access to US technology.

Department of Commerce officials have said they haven’t seen evidence that SMIC can make the 7nm chips “at scale,” a point echoed by ASML’s Chief Executive Officer Peter Wennink.

If SMIC wants to advance its technology without ASML’s state-of-the-art extreme ultraviolet lithography systems, the Chinese chipmaker will not be able to produce chips at a commercially meaningful volume due to technical challenges, Wennink told Bloomberg News in late January.

“The yield is going to kill you. You’re not going to get the number of chips that you need to have high volume chip production,” he said. ASML has not been able to sell its EUV systems to China as the Dutch government has not issued a license allowing those exports.

The US, meanwhile, is pressing allies including the Netherlands, Germany, South Korea and Japan to further tighten restrictions on China’s access to semiconductor technology. That effort is proving controversial and meeting resistance in some countries, as it imposes limits on trade at a time that Chinese businesses are investing in equipment and computational power to compete in the artificial intelligence race.

Huawei may be China’s most promising candidate to develop AI chips to compete with the US. Industry leader Nvidia Corp.’s CEO, Jensen Huang, in December called the Shenzhen firm a “formidable” rival.