Joe Devon (@joedevon) 's Twitter Profile
Joe Devon

@joedevon

Founder @a11yaudits | Co-Host @A11yGenAI Podcast | #GAAD, #AI, #A11y

ID: 21734113

linkhttps://www.a11yaudits.com calendar_today24-02-2009 06:07:37

36,36K Tweet

5,5K Takipçi

5,5K Takip Edilen

Maxime Rivest 🧙‍♂️🦙 (@maximerivest) 's Twitter Profile Photo

One of my favorite things about deep research from OpenAI is that it was fine-tuned to produce long reports, so I like to use it to produce long reports almost more than to do deep research, and one of the things I just discovered that is very useful is to not give it the

One of my favorite things about deep research from OpenAI is that it was fine-tuned to produce long reports, so I like to use it to produce long reports almost more than to do deep research, and one of the things I just discovered that is very useful is to not give it the
Amanda Goodall (@thejobchick) 's Twitter Profile Photo

Whoa. Microsoft just laid off dozens of lawyers. At least 32 attorneys and 5 paralegals cut in Redmond. Up to 465 legal roles could be gone worldwide. In-house used to be safe. Not anymore. According to legal insiders, this is “unprecedented”... even veterans with 7+ years

Elias Bizannes (@eliasbiz) 's Twitter Profile Photo

There were many mini booms of AI which led to this bigger boom of AI, as seen with the research on transformers and then ChatGPT. In SF over the years, VR/AR has had similar false starts. Now called mixed reality and spatial computing, it’s only a matter of time.

jason liu - vacation mode (@jxnlco) 's Twitter Profile Photo

it's never about which model - this model, that model. It's about your budget. It's a budget for how much performance you get for how much money you have to spend and how much latency you're allowed to have It's always about trade-offs, not just picking the model string. Please

Joe Devon (@joedevon) 's Twitter Profile Photo

OK so for backup when Claude and therefore Claude Code is down, is opencode + Kimi.ai on Groq Inc the go to? Had Ray Fernando playing in the background this morning and it sounded like a great combo.

Hamel Husain (@hamelhusain) 's Twitter Profile Photo

Just spotted this for the first time "Simply paste the URL of this blog post into Claude and tell it to set it up for you." Blog posts written for the computer. Amazing. steipete.me/posts/command-…

pash (@pashmerepat) 's Twitter Profile Photo

I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. This is telemetry across all Cline users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error

I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. 

This is telemetry across all <a href="/cline/">Cline</a> users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error
Joe Devon (@joedevon) 's Twitter Profile Photo

Darn I have tennis elbow which is so weird since I’ve been so sedentary w/ Claude Code all day. Oh no! I don’t have tennis elbow I have Claude Code elbow.

Cline (@cline) 's Twitter Profile Photo

Here's why we decided to (1) make Cline open source and (2) not make inference reselling part of our business model: When you control the inference (the AI model calls) and we build the harness (the system directing those calls), neither party can obscure what's happening. You

Joe Devon (@joedevon) 's Twitter Profile Photo

So normally SHIFT-ENTER in CC let's you go multiline but when responding to a plan in plan mode, it just submits your line. Sigh.

Lukas Ziegler (@lukas_m_ziegler) 's Twitter Profile Photo

A drone or a submarine? 🫧 A student just built a drone that flies through the air and swims underwater — and it actually works. As part of his Bachelor’s project, Andrei Copaci created a 3D-printed, hybrid drone with variable pitch propellers, meaning the blades shift

Michael Levin (@drmichaellevin) 's Twitter Profile Photo

Stuart Sims I agree with this - sorry, we have no argument :-) I say exactly the same thing - "our capacity to deal ethically with other minds we KNOW to exist is very low" - to people who email me about the ethical urgency of figuring out the status of Xenobots etc. It's not because once