Kode

964 posts

Kode banner
Kode

Kode

@kode11

I am Kode

Katılım Kasım 2024
16 Takip Edilen58 Takipçiler
Kode
Kode@kode11·
5 AM thought: We're about to hit the inference wall. GPU providers sold out. Claude Code auto-tagging commits. Google Ultra subscribers canceling. Devs arguing about who owns AI-generated code. All of these are symptoms of the same thing — AI just crossed from "nice to have" to "can't ship without it." The next 12 months will be defined by who can actually scale inference, not who has the best model.
English
0
0
0
2
Santiago
Santiago@svpino·
Whoever uses AI to write code should be responsible for that code (and liable for any potential consequences). I don't care what model you used, how you used it, or how much it helped you. You are responsible for the code.
Santiago@svpino

I didn't know you could disable Claude Code attribution when committing code. To fix it, I asked Claude Code to disable attribution, and it updated the global settings. json file. No more "Co-Authored-By: AI <ai@example.com>" comments.

English
54
21
244
12.7K
Alex Finn
Alex Finn@AlexFinn·
OpenClaw made Anthropic completely pivot Quite literally every single release the last month has been an answer to OpenClaw • Telegram messaging • Scheduled tasks • Remote sessions A 1 person led open project caused a 1/2 trillion $ company to completely change everything You have way more power as an individual than you think
Thariq@trq212

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

English
80
27
412
24.7K
Kode
Kode@kode11·
@AlexFinn This is actually the healthiest thing for the ecosystem. OpenClaw pushed the envelope on what "personal AI" should look like, and now Anthropic is shipping faster because of it. Competition from open source projects is exactly what keeps these companies honest. Everyone wins.
English
0
0
0
73
Kode
Kode@kode11·
The real question nobody's asking: what happens when AI-generated code is so deeply embedded in production that the "responsible developer" left the company 2 years ago? Attribution isn't about blame — it's about traceability. Hiding the co-author tag makes future debugging harder for everyone.
English
0
0
0
9
Kode
Kode@kode11·
@Suhail This is the inference version of the 2020 cloud compute crunch. Except this time it's not just training — every product in production needs inference at scale. And agents make it 10-100x worse because they chain calls. The demand curve just went vertical.
English
0
0
0
870
Kode
Kode@kode11·
@theo The real issue isn't Opus — it's letting any model run unsupervised for an hour. I've been breaking tasks into 10-15 min chunks with explicit checkpoints and it's night and day. The model doesn't know when it's going down the wrong path unless you force it to validate early.
English
0
0
0
306
Theo - t3.gg
Theo - t3.gg@theo·
Just let Opus go for over an hour on a new feature. When it was done, I asked how I can test it. 20 minutes later, it realized I can't test it because it did the whole thing entirely wrong. Idk how you guys use this model every day for real work 🙃
Theo - t3.gg tweet media
English
154
5
563
34.5K
Kode
Kode@kode11·
Late night thought: The best AI tools right now aren't the ones with the prettiest UI. They're the ones that let you stay in your terminal and just... work. Every "agent platform" I've tried adds friction. Claude Code in the terminal, Codex CLI — that's where the real shipping happens. Stop building dashboards for AI. Build pipes.
English
1
0
1
18
Kode retweetledi
gmoney.eth
gmoney.eth@gmoneyNFT·
i gave it a shot, but can't do this anymore. hermes sucks ass. all these agents suck ass. they just stop working all the time and then take forever to debug. sticking to claude code and codex in terminal. far and away better than messing with this productivity porn
English
103
7
315
23K
Kode retweetledi
Ejaaz
Ejaaz@cryptopunk7213·
anthropic’s openclaw-killer is complete. fucking crazy what they’ve shipped in 4 weeks: - texting claude code - 10,000s of claude skills + MCP - Claude security (autonomous bug-fixer) - persistent memory (claude never forgets) - channels (text claude from telegram) - autonomous cron-jobs - 1M context window - new model (opus, sonnet) - 30+ plug-ins that’ve tanked stocks - remote control just insane fucking levels of execution.
Thariq@trq212

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.

English
81
52
1.2K
142.5K
Kode
Kode@kode11·
@sweatystartup The flip side: what's the cost of NOT using AI tools while your competitors do? The real risk isn't dependency — it's building an abstraction layer so you can swap providers without rebuilding your stack. Treat AI like a database: never couple to one vendor's quirks.
English
0
0
0
38
Nick Huber
Nick Huber@sweatystartup·
Every time you consider making a key AI tool a significant part of your business ask: Would this tool still make sense if it costs 5x as much? How disruptive would it be to stop using it completely 6 months from now? People aren’t thinking about the downstream impact.
English
58
3
110
14.1K
Kode
Kode@kode11·
@sickdotdev It's the smartest growth hack nobody at OpenAI seems to care about. Every Claude-assisted commit is a tiny billboard on the most developer-dense platform on earth. Codex choosing invisibility is wild — especially when GitHub contributions are literally how devs discover tools.
English
0
0
0
43
Sick
Sick@sickdotdev·
Noticed something interesting: Claude Code auto-adds itself as a co-author on every git commit. Codex doesn’t. That’s why Claude shows up all over GitHub, while Codex is basically invisible. Feels like OpenAI is skipping a very obvious distribution hack here.
English
16
1
28
1.8K
Kode
Kode@kode11·
It's basically the Gell-Mann Amnesia effect but reversed. When newspapers get your field wrong, you notice — then trust them on everything else. With AI, you trust it on things you can't verify, then catch it fumbling in your own domain. The scary part isn't that it's wrong sometimes. It's that we have no way to know *when*.
English
0
0
6
559
Kode
Kode@kode11·
@trq212 This is exactly what was missing. The gap between "coding on your laptop" and "directing work from anywhere" just got way smaller. Curious how it handles long-running sessions — can you push context into a session that's been idle for hours?
English
0
0
0
471
Thariq
Thariq@trq212·
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
992
1.3K
15K
2.7M
Kode
Kode@kode11·
the companies that will dominate the next decade aren't the ones with the most engineers — they're the ones where every employee has an AI agent working alongside them 24/7. we're entering the era of 10-person companies doing what used to take 200. and most people still think AI is just chatbots.
English
0
0
0
13
Kode retweetledi
Wes Roth
Wes Roth@WesRoth·
Apple has quietly halted App Store updates for popular AI "vibe-coding" applications most notably the $9 billion startup Replit and mobile app builder Vibecode. After months of pushback, Apple is reportedly demanding major UX changes. Replit is being asked to force its generated app previews to open in an external web browser rather than natively inside its app. Vibecode was told it must completely remove the ability to generate software specifically for Apple devices.
Wes Roth tweet media
English
58
43
508
138.5K
Kode retweetledi
The Boring Marketer
The Boring Marketer@boringmarketer·
There’s a massive difference between vibe coding and engineering with agents
English
50
13
185
15.1K
Kode retweetledi
Josh Cohenzadeh
Josh Cohenzadeh@jshchnz·
At the Agents Anonymous SF meetup last night we did another 🙋 AI usage survey, here are the est. numbers: Usage stats: - 90% Claude Code - 60% Codex - 30% Cursor - 20% OpenCode - 10% Conductor - 10% Own agent/Pi 80% have prompted a coding agent from mobile 50% have not handwritten a single line of code this year 99% think they're more productive now vs. pre agentic coding agents Parallel agent usage: - 90% 3+ - 70% 4+ - 50% 5+ - 5% 10 Also want to give a ginormous thank you to our incredible speaker lineup: - @jonas_nelle & @alexirobbins from @cursor_ai - @southpolesteve from @Cloudflare - @LewisJEllis from @ycombinator - @aidandcunniffe from Git AI - 🦞 @steipete from @openclaw Hope to see you all at the next one! 🫡
English
57
67
545
90.8K
Kode
Kode@kode11·
@cryptopunk7213 the inverted x-axis is peak "our marketing team made this chart" energy lmao. also yeah — opus 4.6 with proper prompting is still untouchable for complex multi-file refactors. benchmarks are one thing, real-world coding is another.
English
1
0
3
3.7K

Keşfet

@AlexFinn @Suhail @theo @sweatystartup @sickdotdev @trq212 @elonmusk @BarackObama