hboot (@hboot0230) header
hboot (@hboot0230) profile picture

Frontend developer building AI products. Sharing my journey from ideas to real products.

Joined January 2024
Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)Photo by hboot (@hboot0230)
hboot retweeted
A new Docker, but a familiar story. Today we're introducing a new look, a new focus, and a refreshed Moby. Same Docker you've trusted for over a decade, now built to run on trust in the agentic era. We can't wait to show you. Read the full story: bit.ly/4iX61ek
351
609
445
7,988
1,326,066
hboot retweeted
Heads up, we’re starting to test dots with a small number of ChatGPT Plus users. Looking forward to the continued feedback as we expand and I’m recently seeing a lot more positives around how good the proactivity has been after many improvements. We’re also bringing dots to all ChatGPT Business Standard users. Rollout will start today.
1,337
673
618
10,109
1,595,493
hboot retweeted
I took this to heart and spent the last few hours doing another deep dive on GPT-6.2 Astra tl;dr - things are better than when I tested, but IMO still "directionally, very bad" I'm going to keep using the same example I've hyperfixated on since the start: "why is creating a worktree so slow?" I had a long thread trying to diagnose perf issues while using t3 code on a particular VPS. 2 of the 3 were fast, 1 was really slow. I asked astra outright "why is this so slow?", and it said a bunch of gibberish. I followed up with "I feel like I'm going insane, can you just tell me the cause of the slowness?" I'll give you the answer upfront: this VPS uses a virtual disk that is slow as shit, my other VPSs have physical NVME drives that are faster. Image 1 is from before the fixes Tibo mentioned. It shows an unnecessary graph, focuses too much on pnpm and file systems, bolds irrelevant text, and brings up ram just as much as it (subtly) mentions drive speed. Image 2 is of Opus asked same thing. It opened with the important part in bold: "Slow disk, made worse by VDO". Ideal! Image 3 is 6.2 Astra post-fixes Tibo mentioned. Better? Absolutely. Much more concise. Sadly, it still focuses way too much on second-order problems that are a small % of the cause. "XFS over a compression and deduplication layer on a virtual disk." - so close, but still a miss. I think this perfectly encapsulates the problem I have with 6.2 Astra. It doesn't miss anything. It's SO thorough. But in it's thoroughness, I find it misses the most important thing: the actual point. It wants to know everything, and then it wants to share everything. It doesn't understand what is and isn't important. Did it say anything wrong in my screenshots? Not really. But IMO, it still entirely failed to miss the point of my question, and gave an answer that was too focused on accuracy and not enough on clarity. In the wise words of Michael Seibel: "Most aim for 100% accuracy, and they end up with 50% clarity. Aim for 100% clarity, 80% accuracy". Silly way of putting it, but I genuinely wish OpenAI models would lie to me a LITTLE more so I could better understand the vibe, instead of having my time wasted by all these useless details.
One of the funny reasons for the difference in vibes between the influencers and the crowd today on 6.2 Sol/Astra is that we gave a few folks access a while ago and then made a lot of changes in the last 3-4 days and I'm pretty sure no re-testing was done within those days and the videos were produced last week. Don't get me wrong, while the models are a hefty jump compared to their GPT predecessors, they are by no means perfect and there are a few things the teams are excited for the models to get better at in future iterations in terms of taste and niceness of use. Love all the feedback and we hear you!
287
89
72
3,002
453,375
hboot retweeted
上个月的体检报告,我交给了开源项目 Mirobody,在自己 Mac 上从读报告到回答问题全跑通了,没填一个 API key。58 行化验数值逐项对过原件,全对。可第一次上传时,化验单那几页它一条都没读进来。 装法:Homebrew 装 llama.cpp 跑模型,colima 起 Docker 跑应用,设置页选「100% 在本机运行」,用默认的小模型 minicpm5-2b,读图交给 glm-ocr。模型下载加载 6 分钟。机器是 M4 Pro、48GB,模型走 Mac 的 GPU。 第一次传整份 14 页的 PDF,1 分钟处理完,进来 33 条,全是前几页的查体和结论,化验单 3 页一条没有。翻日志,读图的模型一次都没被调用。这 3 页是嵌在 PDF 里的扫描图,页眉页脚却是文字,按文档写的规则,有文字层的页不走 OCR。 我把这 3 页截成图片单独传,一分半处理完,58 行化验结果全进来了,数值和原件逐项对得上。错了 3 处小地方:红细胞的参考范围多读出一个「1」,一个项目名丢了个字,甘油三酯旁边印的上箭头没记下来。 Mirobody 主要干的事,是把每条读数对到标准编码 LOINC,不同医院、不同写法的同一项才能连成一条线。这 58 行对上了 20 行。生化、甲功、糖化基本都对上了,单位不同还会选不同的编码;血常规 22 项、尿常规 14 项一项没对上,卡在「白细胞WBC」这种中文直接连着缩写的写法上。 最有意思的是肌酐。报告上写的是「肌酐(Cre)」,而 Cre 在 LOINC 里查到的是一种耐药菌的培养检查。它判断这个名字有歧义,就留空,没有瞎猜。 然后我问它:「我这次体检有哪些指标超出了参考范围?」2B 小模型想了 84 秒,走了 11 步。报告上标了箭头的 5 项全找到了,但把一项在范围内的血糖也算成了超标。它查表没拿到数值,转头去翻了原文件,回答里的数字也没带来源链接。我的血脂和肝功能确实有几项偏高,具体数值就不放了。 接 Claude Code 这一步,我换成了项目自带的演示账号。MCP 接上以后,Claude Code 查到的读数会发到 Claude 的服务器,所以这一步没用我自己的数据。问它「胆固醇这几年怎么变的」,只有一条记录的时候,它直说看不出变化,没编趋势;我再传两份合成报告(一份 PDF、一份 CSV,写法不完全一样),三次读数被认成同一项,按日期排好,每个数字都标了出自哪个文件。 ChatGPT Health、阿福是厂商的云服务,注册就能用。Mirobody 是 Theta Health 开源的(Apache-2.0),国内的网页版和微信小程序也基于它。开源版能把记录和模型都留在自己电脑上,代价是得自己折腾,小模型也慢。它不做诊断,那次回答最后一句也是让我拿报告去问医生。 认不出的写法可以去提 issue,它的词表就是这么一行一行补起来的。 github.com/thetahealth/mirob…
70
43
30
50
13,577
중국의 한국에 대한 이번 최혜국 대우 합의는 한중관계의 전면적 실질적 복원을 넘어, 한중관계의 새로운 미래를 만들어나가는 토대가 될 것입니다. 대중협상에서 큰 역할을 해 준 우리 정부 공직자 여러분 수고 많으셨습니다. 감사드립니다. 국민여러분께서도 맡은 일 잘 해낸 외교부 문화체육부 산업부, 청와대 안보실 정책실 등 공직자들을 많이 격려해 주십시오.
1,497
1,853
345
15,947
1,545,458
Gemini 4 Neon: frontier-level intelligence with fast end-to-end task completion across complex software engineering, knowledge work, and science workflows. Begins rolling out today in the Gemini API in @GoogleAIStudio, Gemini for business, for paid Google AI Pro and Ultra subscribers in Google @Antigravity, and for Google AI Pro and Ultra subscribers in the @GeminiApp.
912
1,490
689
18,533
2,117,935
We’ve priced our IPO at $83 per share, with trading expected to begin on Nasdaq tomorrow. anthropic.com/news/anthropic… Legal disclaimer: A registration statement relating to the Class A common stock was declared effective by the Securities and Exchange Commission on November 18, 2026. The offering is being made only by means of a prospectus. Copies of the final prospectus may be obtained, when available, from: Goldman Sachs & Co. LLC, Attention: Prospectus Department, 200 West Street, New York, NY 10282, by telephone at (866) 471-2526, or by email at [email protected]; or Morgan Stanley & Co. LLC, Attention: Prospectus Department, 180 Varick Street, 2nd Floor, New York, NY 10014, or by email at [email protected]
1,289
2,187
1,381
16,941
3,370,084
hboot retweeted
Tell Grok an idea, and it builds a working version live in your chat. Grok Build is now available on every plan - on web, iOS, and Android.

536
533
50
7,161
74,831,686
hboot retweeted
GPT-6.2 Astra is pretty good at hard things. Here the team shared some results on AMD and Jalapeño chip optimizations. I do get the feedback on its communication style and we're working on that, but for really the hardest tasks in the world it does seem to be in a league of its own at the moment.
Working with @AMD, our models identified up to 14% PPA improvement on flagship GPU IP in less than five months—building on designs AMD’s engineers had already spent years optimizing. The same approach helped improve Jalapeño, our first custom inference chip, with gains verified on real silicon. New evaluations also show our models getting better at certain chip design tasks. We’re sharing these results and how we’re working with @Synopsys to bring our model capabilities and their trusted EDA design and validation tools to more chip designers. openai.com/index/advancing-c…
892
144
59
4,165
609,297
hboot retweeted
F*CK IT $10 for $500 GLM 5.3 till end of the week
we're bored we're just gonna do phase 2 now $200 of GLM 5.3 usage for $10 have fun
749
519
552
10,547
919,950
Fuck Anthropic, seriously.
234
180
17
4,443
231,644
hboot retweeted
On November 16, malicious JavaScript was served via Optimizely's CDN to visitors of 100+ major sites such as Zoom, the BBC, and CNN. The attack swapped crypto wallet addresses, skimmed card info typed into forms, and loaded iOS exploit code. Attackers stole ~$7k from victims.
65
344
28
5,032
348,456
hboot retweeted
Some of you have been asking very politely. Some of you have just been asking. GPT-6.2 Astra and Sol are now available. Super efficient and built to perform where it counts—the real world. openai.com/index/introducing…
2,278
3,607
3,720
35,949
11,953,256
hboot retweeted
Node.js 27.0.0-alpha.0.1.1 (Alpha) is out 🚀 Notable changes: the darwin tarballs now ship a notarized bin/node, plus V8 and nghttp3 updates. Read the release notes: nodejs.org/en/blog/release/v…
4
47
4
411
29,020
Claude writes better code when it can verify its work. Checks that used to be expensive, like tests, benchmarks, and end-to-end runs, are now cheap. Here’s how the Claude Code team thinks about verification: claude.dev/blog/how-the-clau…
375
896
261
14,949
1,814,418
hboot retweeted
Buttons
69
412
29
4,585
109,827
hboot retweeted
一个 logo,15 秒,就变成了一条发布视频。 我没写一句剪辑指令。 只把苹果的 logo 丢进 YouArt,说了一句:做一条 15 秒发布动效。 Agent 自己读 SVG、排镜头、渲动效、配中文配音和字幕,黑底淡入、桌面端生成中、最后发光收尾,全是它自己排的。 它能这么排,是因为 logo 是矢量图:线条和形状都是干净的数据,Agent 不用猜轮廓,直接拿形状做淡入、描边、发光,动效才干净。 人只做一件事:给它一个开头。 你手头有没有一个 logo,也想让它动起来? youart.ai?invite=iljomw
25
15
6
13
2,048
We've tweaked flowchart movement to make it more intuitive.
3
6
124
4,716
hboot retweeted
OpenCode Browse 0.1.0 is now released it is rewritten in rust: - 25x less memory - 23x smaller - removed dependency on playwright and browser operations are exposed directly to your agent
216
316
79
8,318
408,297
hboot retweeted
Hy4 flash is free with near-unlimited usage for the next 2 weeks 1M context · Multimodal · ZDR Hy's fastest and most cost-efficient model
150
222
107
5,116
369,887