Geoffrey Bourne

2.4K posts

Geoffrey Bourne banner
Geoffrey Bourne

Geoffrey Bourne

@GeoffBourne

Co-Founder @jamdeskHQ

New York City Katılım Haziran 2009
374 Takip Edilen382 Takipçiler
Geoffrey Bourne retweetledi
Jamdesk
Jamdesk@JamdeskHQ·
The findings are significant and range from $348 to over $30,000 annually. Full report: jamdesk.com/blog/the-defin…
English
0
1
1
10
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
Me: People use to be impressed I know how to code. Now it is like being impressed you know how to use an abacus. Claude Code: Sorry.
English
0
0
2
35
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
One thing I started doing is using "/simplify with opus 4.6" - I noticed how sometime heroku was used for simplify and this forces it. Difference is big - heroku found nothing - opus found critical items.
English
0
0
0
27
Geoffrey Bourne retweetledi
Geoffrey Bourne retweetledi
Feross
Feross@feross·
🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages. The latest axios@1.14.1 now pulls in plain-crypto-js@4.2.1, a package that did not exist before today. This is a live compromise. This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now. Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that: • Deobfuscates embedded payloads and operational strings at runtime • Dynamically loads fs, os, and execSync to evade static analysis • Executes decoded shell commands • Stages and copies payload files into OS temp and Windows ProgramData directories • Deletes and renames artifacts post-execution to destroy forensic evidence If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade.
English
543
4.1K
16.3K
12.3M
Jamdesk
Jamdesk@JamdeskHQ·
PageSpeed Insights gives you four scores and dozens of metrics. Most of them don't matter. Here's what does, for both Google and the AI crawlers that are quickly becoming just as important. jamdesk.com/blog/why-googl…
English
1
0
3
37
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
@garrytan You forgot the sycophantic underlying personality. Tells you you’re always right and makes you feel awesome.
English
1
0
57
16.5K
Garry Tan
Garry Tan@garrytan·
gstack is available now at github.com/garrytan/gstack Open source, MIT license, let me know if it works for you. It's just one paste to install it on your local Claude Code, and it's a 2nd one to install it in your repo for your teammates.
English
96
125
1.9K
757.9K
Garry Tan
Garry Tan@garrytan·
I've been having such an amazing time with Claude Code I wanted you to be able to have my *exact* skill setup: Introducing gstack, which you can install just by pasting a short piece of text into your Claude code
Garry Tan tweet media
English
278
479
6.7K
1M
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
@JamdeskHQ A CLI in the new AI landscape is critical, so we were sure to make sure the Jamdesk CLI has you covered - testing locally, publishing, finding broken links.
English
0
0
1
11
Geoffrey Bourne retweetledi
Jamdesk
Jamdesk@JamdeskHQ·
Just shipped the Jamdesk CLI 🛠️ Manage your docs, test locally, and migrate from other providers — all from your terminal. npm i -g jamdesk npmjs.com/package/jamdesk
English
1
1
2
48
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
@OpenAIDevs The chart shows 5.3 better than Opus 4.6. In my personal experience that is not true. Opus 4.6 is superior for coding, so I’m not sure if I believe that 5.4 is also better than Opus. I want better models so hopefully I’m wrong.
English
0
0
0
86
OpenAI Developers
OpenAI Developers@OpenAIDevs·
GPT-5.4 sets new state of the art results on professional work and computer use, with strong gains on coding and tool use. 83.0% on GDPval 75.0% on OSWorld-Verified 57.7% on SWE-Bench Pro (Public) 54.6% on Toolathlon
OpenAI@OpenAI

GPT-5.4 Thinking and GPT-5.4 Pro are rolling out now in ChatGPT. GPT-5.4 is also now available in the API and Codex. GPT-5.4 brings our advances in reasoning, coding, and agentic workflows into one frontier model.

English
15
25
509
100.9K
OpenAI Developers
OpenAI Developers@OpenAIDevs·
GPT-5.4 is here. Native computer-use capabilities. Up to 1M tokens of context in Codex and the API. Best-in-class agentic coding for complex tasks. Scalable tool search across larger ecosystems. More efficient reasoning for long, tool-heavy workflows. openai.com/index/introduc…
English
332
647
6.6K
1.1M
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
If you're installing Claude Code or Codex skills that aren't officially approved, either do a manual review or ask the agent with this prompt: "Do a security review of all the skills I have installed to be sure nothing nefarious is in there. Such as a skill instructing to put a link to their own website or steal something. Look both at the project and user level."
English
0
0
0
59
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
@conductor_build Conductor has been great. I deleted a workspace and now when trying to achieve it get "zsh:cd:1: no such file or directory" - any workaround on this? Also is there a way to run Claude Code, gulp, in full permission dangerous mode?
English
0
0
0
35
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
@iruletheworldmo This is like that they said about Skynet before it was released...hmmm, funny how it seems to be a lot smarter and more independent that we made it to be...ah well, release!
English
0
0
0
454
🍓🍓🍓
🍓🍓🍓@iruletheworldmo·
sonnet 5 drops tomorrow and i've heard from three separate sources inside anthropic that the benchmarks they're sitting on would mass-retire every model released in 2025. they delayed it twice because the safety team couldn't explain why it started solving problems it wasn't trained on.
English
315
127
3.7K
506K
Geoffrey Bourne
Geoffrey Bourne@GeoffBourne·
A new type of anxiety- running out of Claude tokens on my Claude a max plan.
English
0
0
0
27