Cole Codes
141 posts
Cole Codes
@itscolecodes
Shipping software, not vibes (ok, sometimes vibes). https://t.co/7JZn6QvPtl privacy-first AI face swap.
London, UK Inscrit le Ocak 2026
47 Abonnements7 Abonnés
@TheGeorgePu I really feel sometimes DeepSeek outdoes Opus because it’s guardrails are much looser
English
I ran Claude 4.8 Opus against DeepSeek V4 Pro.
Blind. Four tests. Separate agents judged.
DeepSeek won 4-0.
It's also 12x cheaper.
Here's the part that stuck with me.
I did the math, and Claude is maybe 5% better.
We're paying frontier prices for a 5% edge and a nicer personality.
Relying on one lab is a strategic mistake.
English
@harshilmathur On Hermes I hook up an aux model that describes the image back to the main model
English
I’m sure GLM 5.2 is great, but how are people coding with models that can’t see?
When something breaks, are you just copy-pasting errors and describing issues manually? That sounds painful in general, but especially for frontend.
English
Codex **had** a bug. Fixed.
More feedback. Better product. Keep it coming.
Uzi@uzairansar
So Codex has a bug that could kill your SSD in under a year...
English
Introducing Hubble: the best notepad for you and your agents.
- Feels like Notion or Apples Notes, but for Markdown
- Live-reloading editor to collaborate with agents
- Supports HTML-based apps to build interactive visualizations
Free and open-source 👉 hubble.md
English
I'm REALLY not trying to be a hater... but why is this a priority over building more robust agents/tools/skills?
Nous Research@NousResearch
Your Hermes Agent can now adopt an animated pet: a small sprite that reacts to what the agent is doing (idle, running a tool, thinking, waiting, finishing, failing) in the GUI or TUI. You have nearly 3000 pets to choose from via the petdex gallery, or you can submit your own.
English
GLM 5.2 is *not* cheap
$42.38 for a review workflow in Claude Code
it burnt A LOT of tokens
but most importantly, was it worth it?
so I asked Opus 4.8 (Max) + GPT 5.5 (High) to evaluate the review
most of it was useless
a lot of was contradicting information, despite running through a verification workflow
but there were some solid changes that lead to a PR (which I had Claude implement after filtering)
my read on this:
GLM 5.2 is not a bad model, but that it is nowhere near as good or as cheap as people make you believe
the most interesting thing about this model is that it is pretty good, better than any other open source, and that it is truly open
this will be the last time I used it
English
I see a lot of people hyped about GLM-5.2. Rightfully so! Having an open weight model surpass GPT-5.4 and every Gemini model is dope.
That said - it's not cheap. Both Opus 4.8 and GPT-5.5 set to "medium" are cheaper and smarter than GLM-5.2
English
Spent a lot of time using GLM 5.2.
I’ve always been skeptical of the Open Models, as they’ve never lived up to the benchmarks and announcements.
This is the first model that passes the vibe check.
This feels like a DeepSeek R1 moment that will push the frontier labs into releasing even better models.
Time to buy a BEAST computer to run these models on.
English
I feel like Claude Code limits have been HUGELY increased. I think they’ve been paying attention to the bad press
English
Tip of the Day: Did you know you can share your hermes agent profiles onto github?
Share a profile and others or yourself can download and distribute it with ease!
See the docs here: hermes-agent.nousresearch.com/docs/user-guid…
English
@theo Honestly I’m finding it lazy but probably a skill issue right 😂
English
@sflorimm DeepSeek v4 is getting an unreal amount of usage through openrouter
English
We're fixing a codex bug today that was causing us to undercount tokens being served to some Pro and Plus accounts by a small amount. This impacted < 15% of accounts.
Not the kind of bug you want us to fix, but didn't want to do this silently and thought you should know.
English
hate to tell you but
everyone outside of our bubble uses claude code
just came from a group business coaching call
literally everyone was mind blown by claude code
English
Codex is now insane for internal tools.
Any app you want, hosted with new Codex sites feature
& Convex just released a plugin today so you can easily add db....
Very fast and easy to use.
Clean "Sites" tab shows all the sites you're building.
However, you can't make the sites public (yet)
English
English
Did not expect OpenAI to "compete" with my new project before I even dropped it 🙃
This is a cool feature. Nice to see OpenAI and I see the same hole in the market.
Don't worry though, Lakebed is 10x cooler than their version :)
Rohan Varma@TheRohanVarma
We just launched Sites into Codex! Software creation was always about more than writing code. Sites in Codex fundamentally gives the power of end-to-end software creation to every user, no matter their technical fluency. These Sites are fully deployed to a URL, private to workspaces, come with authentication, can have static files, and can store dynamic data in databases. It is in preview for business and enterprise teams and will be rolling out to all workspaces over the next day. Give it a try by typing @ Sites into Codex and ask it to build anything! This project took a massive amount of effort across hundreds of people at OpenAI - proud that we were able to get this out and excited to see what you all build with it!
English
🚀 Codex app update
🌐 Sites plugin: deploy apps, dashboards, and games on OpenAI hosting
🗂 Sidebar project manager with env vars and secrets
🔐 Business default; Enterprise via RBAC
Changelog: #codex-2026-06-02" target="_blank" rel="nofollow noopener">developers.openai.com/codex/changelo…
English
