Bessi

2.8K posts

Bessi banner
Bessi

Bessi

@LLMpsycho

I'm just a coder for fun, like Saitama, suffering from LLM psychosis.

Albania Beigetreten Temmuz 2024
1K Folgt996 Follower
All day Astronomy
All day Astronomy@forallcurious·
BREAKING🚨: A new heavily mutated COVID variant has been detected in 25 states.
All day Astronomy tweet media
English
441
319
1.9K
183.2K
Bessi retweetet
Shaniqua Posting Delusions
Shaniqua Posting Delusions@DeIudedShaniqwa·
How life feels since X replaced indian slop with racist japanese content
English
108
1.4K
27.3K
267.1K
Bessi
Bessi@LLMpsycho·
@HarryStuck77 @droid Latest updates have improved it further. I'm at that point where i have everything to code, i dont anything else.
English
0
0
1
43
Harry Stuckler
Harry Stuckler@HarryStuck77·
A professional approach starts with a lot of planning. @droid is on top of this game. Not just a plan and a task list. A proper validation contract.
Harry Stuckler tweet media
English
1
0
19
609
Bessi
Bessi@LLMpsycho·
私はここで何人かの日本人開発者をフォローしたいと思っています。
日本語
0
0
0
9
Bessi retweetet
🍓🍓🍓
🍓🍓🍓@iruletheworldmo·
openai’s new model spud isn’t just an incredibly powerful and chonky new model. it’s that as well but it’s a a refocusing of their attention on what really matters. serving people with an always on intelligence that can serve them. they’ll pull together agent mode, atlas, deep research, codex, etc etc. into one unified agi experience with a model that feels alive and vastly more capable than its competitors people at openai are shocked enough at the progress of this model they felt comfortable wiping out all the efforts made with sora and any billion dollar disney deals you don’t create an ai deployment division. unless. you. built. a.g.i. let that sink in gremlins.
English
86
31
649
62.3K
Bessi
Bessi@LLMpsycho·
@Hamzaa_i This mission finished without problems. I have also stopped it several times manually because i moved from work-home-coffee bar-home-tethering from phone
English
0
0
0
15
Hamza
Hamza@Hamzaa_i·
@LLMpsycho I’m still having problems in long missions at least with 5.4 but there’s a work around
English
1
0
0
10
Bessi
Bessi@LLMpsycho·
Droid Mission in a nutshell, 24h + running. Damn.
Bessi tweet media
English
7
2
28
1.8K
Eric Glyman
Eric Glyman@eglyman·
We only hire builders (and we’re on a hiring spree)! Reply with something you've built. I'll read them personally. We’re interviewing the best ones. You’ll be a good fit if you: - work best without permission - default to “how could I automate this” - had weird teenage hobbies - spend your sunday making side projects - have more Claude agents than cousins - shipped something this week - make prototypes, not powerpoints - don’t like hierarchy - are good at games: chess, monopoly, poker - would take dinner with Elon over $100k Good luck, Eric
English
471
103
2.6K
550.4K
Bessi
Bessi@LLMpsycho·
@Hamzaa_i compacting was failing 3 months ago,now never had such problems.
English
1
0
0
49
Hamza
Hamza@Hamzaa_i·
@LLMpsycho Until compacting fails 😕
English
1
0
0
40
Bill
Bill@justBill·
@droid @FactoryAI Is going to win and its not even close. I was trying EVERYTHING to fix my holdout RMSE on a model I am working on and it kept getting caught over and over and even regressing. One prompt using droid + GPT5.4 High and fixed it. I spent almost $100 in Codex credits trying to fix this before hand. If i could I would buy the Max plan TODAY
Bill tweet media
English
6
6
80
7.2K
Bessi
Bessi@LLMpsycho·
@OutVersus_ Claude 200+Codex 200,with CLi proxy
English
0
0
1
119
Bessi
Bessi@LLMpsycho·
@HarryStuck77 Mine not finished yet, will share the total when it does.
English
1
0
1
120
Bessi
Bessi@LLMpsycho·
Codex talking to Slack, Figma, Notion, and Gmail is the part that makes this feel useful.
English
0
0
0
66
Bessi
Bessi@LLMpsycho·
If the Claude Mythos leak is real, the coding race just got louder.
English
0
0
1
117
Bessi
Bessi@LLMpsycho·
@thsottiaux this is the part that makes codex feel useful in real work
English
0
0
0
502
Tibo
Tibo@thsottiaux·
Boom. Plugins! Codex now has access to most things it couldn’t reach before and all super easy behind the same with you use for your ChatGPT account. I use this for *everything*, from managing my calendar, triaging incoming bugs, keeping up to date with what everyone is doing at the company and so much more
OpenAI Developers@OpenAIDevs

We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins

English
83
61
1.1K
157.5K
Bessi
Bessi@LLMpsycho·
@petergostev tracking real repos makes this feel a lot more useful than pure hype.
English
0
0
0
75
Peter Gostev (Visiting SF)
Claude vs Codex - who is winning? The best data I could find to do a fair comparison between the two. It is not ideal, but some rough indication: - Usage: NPM and Homebrew installs - Footprint: repos with .claude/ or .codex/ - And of the repos how many are being actively updated So pretty clear that Claude Code is leading - whether it is 70% of 95% of the this slice of the market is not clear. But at least both are being used actively in real repos. If you have any other ideas for what sources to track let me know.
Peter Gostev (Visiting SF) tweet media
English
12
1
76
8.6K
Bessi
Bessi@LLMpsycho·
@reach_vb Plugins make Codex feel like a real workflow tool, not just a chat box.
English
0
0
0
270