Ody Mbegbu

Software Engineer

[Ody Mbegbu @Odytrice]

@daveddev @rustrover @vlad20012 Will that matter if a developer isn’t really writing the code anymore? At that point, all that matters is the engineering principles like safety and predictability

[Ody Mbegbu @Odytrice]

Many Senior Developers either don't know about this or can't see this far ahead.

It "knows" the internal workings of libraries and it can see potential race conditions due to DI scoping conflicts

And this is GPT 5.5 on "Low Reasoning".

[Ody Mbegbu @Odytrice]

@yegor256 Don’t know if you know this.. But we tried the single POST entry point. It was called SOAP. Bad Idea

[Ody Mbegbu @Odytrice]

@nickchapsas Opus 4.7? or Opus 4.7 + Claude Code?

[Ody Mbegbu @Odytrice]

@DataChaz Deepseek V4 Flash

[Ody Mbegbu @Odytrice]

@rishabhvision @guzmansalv @NielsRogge Still better than being confidently wrong

[Ody Mbegbu @Odytrice]

@MrAhmadAwais It’s “OpenCode” not “OpenModel”

[Ody Mbegbu @Odytrice]

@rez0__ Wake Up Samurai, It’s not over yet

[Ody Mbegbu @Odytrice]

@GergelyOrosz I tried doing this by attempting to distill my own model and it ended up hilariously bad. 😂😂

I did learn a ton along the way

Here’s a monument to my failure

https://t.co/ugBPFj47QD

[Ody Mbegbu @Odytrice]

@TeksEdge @stevibe They were probably running a heavily quantized version. In order for the 3090 memory bandwidth to produce those kinds of numbers

[DHH @dhh]

I've been a K2.5 superfan since it came out. These new numbers for the next version look incredible. You gotta love competition!

[Ody Mbegbu @Odytrice]

This right here is my biggest fear. Tools like Open Code as well as Open Models like Gemma are really the only things in their way.

Now you see why Anthropic sending lawyers at @thdxr was a canary in the coal mine event. The prompt caching excuse was just a pretext

[Min Choi @minchoi]

Anthropic shut down an entire company's Claude access overnight

60+ employees. No explanation. Just an email.

Want to appeal? Fill out a Google Form.

Integrations gone. Histories gone. Everything built on Claude... gone.

Never let one vendor own your workflow.

[Ody Mbegbu @Odytrice]

Now this is some MEGA token consumption

[Ody Mbegbu @Odytrice]

This joke took me multiple seconds to get. 🤣🤣🤣

[Dev Ed @developedbyed]

@claudeai Welcome back opus 4.6

[Ody Mbegbu @Odytrice]

@thdxr Not trying to victim blame but Sam in particular is notorious for all the AI existential rhetoric in order to justify massive valuations. Instead of being honest about it.

To him and the other CEOs it’s a perception game. But to many people, It’s a real existential crisis

[Ody Mbegbu @Odytrice]

@zimwha @GergelyOrosz I agree with you. However it means that any model trained on publicly available code is infringing on copyright.

I’m not so sure that is a thread Anthropic wants to pull

[Ody Mbegbu @Odytrice]

@digitalix Honestly? I wouldn’t mind a 64Gb version of that GPU even if it’s above $1000

[Ody Mbegbu @Odytrice]

Qwen 3.5 - 27B is very underrated. Its performance blew me away. The 35B constantly underperforms by comparison

[stevibe @stevibe]

"122B has to be smarter than 27B"

I showed 4 UI components to three Qwen3.5 models and asked them to recreate them from a screenshot alone:

- 27B (dense)
- 35B-A3B (MoE)
- 122B-A10B (MoE)

Same screenshot. Same prompt. Same task.

Which one do you think nailed it?

[Ody Mbegbu @Odytrice]

@shanselman 8Gb of RAM used to be the standard. And the specs you mentioned is more powerful than a decent PC from 10 years ago.

From a computational standpoint, What has really changed from 10 years ago?

So you are 100% correct. It’s organizational willpower