Binh (@binh) header
Binh (@binh) profile picture

Rails and iOS developer. @twilio Champion. Building an Expensify alternative.

Austin, TX
Joined April 2008
Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)Photo by Binh (@binh)
I pulled my kids out of Apogee for similar reasons.
Replying to @BillAckman
My son attended Alpha from 2020 until recently. Most of the families in our original cohort have pulled their kids over the past two years. Alpha has slick marketing, but there’s been a lot of dysfunction behind the scenes. These are things I personally observed: 1. Persistent teacher turnover. 2. Alpha created a “Dean of Parents” role that acts as a gatekeeper between parents and guides. Direct parent–guide interaction is strongly discouraged. 3. A guide at Alpha’s main campus was disciplined and ultimately fired, in part, for telling a parent that their child was crying daily due to frustration with trying to complete their work in 2 hours. The parent appreciated the transparency. The Dean of Parents objected and attempted to block a scheduled meeting between her and the guide to focus on helping the child. 4. The two-hour academic promise doesn’t hold for most students. Many children struggle to finish their work, some cry regularly, and negative self-talk is common. From what I saw, only about 15–20% of students had an “Epic Day” where all academics were completed. Many kids end up finishing work at home. 5.There’s implicit pressure on kids and parents to speak positively about the school. Alpha does some things well. They have big aspirations. But right now, the hype doesn’t match the reality. I wish them the best.
1
33
Binh retweeted
No one’s a faster typer than an elder millennial who took a keyboard class in middle school.
582
1,653
731
18,491
710,864
Even now, this is a thing in dental radiology.
How many of you are “burn a CD” old ?
19
-----BEGIN RSA PRIVATE KEY----- 4 -----END RSA PRIVATE KEY-----
241
3,988
332
42,187
1,111,727
Can't wait to test M3.1's ability to write prompts for H3.
MiniMax M3.1 Flash: Space Performance + Bunny Speed 🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash. 💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed. API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens. Model weights will arrive on Oct 23. API: platform.minimax.io M Plan: minimax.io/m-plan MiniMax Code for desktop: agent.minimax.io/download
34
This is like the Apple version of the amazing Nike freestyle ad from the early 2000s.
The best intro ever made by Apple 🫪 Apple October (Unleashed) Event
16
Using the configuration from the model card (huggingface.co/nvidia/GLM-5.…) results in almost a 2x increase in single-stream tokens/sec compared to the awesome quant by Brandon Music. The setup also resolves the "locklocklock" issue when going concurrent. Many thanks @NVIDIAAI
47
Working on a new email client.
19
Local models are a good complimentary mental model to the cloud-exit perspective.
Replying to @amybuildsAI
My sheds are all API calls. But a baller shed would also have room for local models. I hope to upgrade to such a shed soon 😄
1
22
Binh retweeted
I was surprised how bad it was just walking from the hotel to the Rails World venue. One strung-out guy wanted to fight me for some reason, another was swinging wildly and swearing profusely. Lots of zombie vibes too. Whatever Austin is doing, it's not working.
2017: Austin spent $35 million on homelessness. 2,036 homeless counted. 2025: $118 million. 3,238 homeless. Spending more than tripled and homelessness went up 59%. If you service the homeless lifestyle, you will get more of it. The NGOs that run this system get paid by the problem of homelessness, so they have no reason to end it -- in fact, their only incentive is to make sure the problem grows.
495
555
89
6,774
2,330,997
Qwen3.8 27B locally easily allays this fear.
My biggest fear as a dev is AI disappearing and I have to sit to learn CSS again.
54
I'm getting excellent results from the following local setup: GLM 5.3 Flash with Zcode for the agentic coding, Qwen3.8 Flash Next for the code review, back to GLM 5.3 Flash to double-check Qwen's review and apply changes. DeepSeek V4 Flash when speed is primary factor
1
50
The snappiness of Omarchy on older hardware is enticing to people I know. The biggest barrier to adoption that I've seen is the lack of desktop UI - it's a mental hurdle that a lot of people can't seem to get over. Yet.
1
60
Truth. I bought one after @patrickc posted about it a few years ago. Now it's my favorite gift to give.
After a month of using it, I can attest: This thing is magic. Whenever you get bit by some bug like a mosquito or a sandfly, you just put this on the bite for a few seconds and the itchiness goes away and it heals way faster.
79
People are sleeping on the quality of @Alibaba_Qwen Code's spinner verbs.
Claude Code leaked their source map, effectively giving you a look into the codebase. I immediately went for the one thing that mattered: spinner verbs There are 187
67
Day-0 support with official quants in NVFP4 and MLX is clutch. Hope this is the norm going forward.
Aloha! 🌺Introducing Ornith-1.5, a family of open-source LLMs spanning 9B Dense, 35B MoE, and 397B MoE, trained with self-improving strategies. It achieves state-of-the-art performance among open-source models of comparable size and delivers performance comparable to Claude Opus 4.8 across reasoning, agentic, and coding tasks: ✅Terminal-Bench 2.1 (86.1) ✅SWE-Bench (86 on verified, 65.1 on pro, 79.6 on Multilingual) ✅DeepSWE (56) ✅HLE (44.6) ✅ClawEval (81.4) ✅Tool Decathlon (71.2) Ornith-1.5 takes a major step toward training foundation models through end-to-end self-improvement, extending the self-scaffolding strategies introduced in Ornith-1.0 into a more complete self-improvement loop: the model proposes new tasks, generates task-specific scaffolds, and produces solution rollouts for reinforcement learning, continuously creating new learning experiences from which it can improve. All models, along with their quantized versions (FP8, GGUF, MLX, and NVFP4), have been released under the MIT License, enabling unrestricted commercial and research use. 📘Tech Blog: ornith.ai/ornith_1_5.html 🤗Huggingface: huggingface.co/collections/o…
1
49
After about a year of heavy usage of coding agents I finally got to see one use "delve". Thanks DeepSeek.
27
I would like to ask for @poolsideai 's Laguna S 2.1 to be benchmarked please.
You asked for it. @SpaceX Grok 4.6, @ZhipuAI GLM-5.3, and @GoogleAI Gemini 3.7 Flash benchmarks dropping on Monday.
53