m-ret

1.9K posts

m-ret banner
m-ret

m-ret

@mretsal

Developer & Entrepreneur. I like AI.

Costa Rica Bergabung Şubat 2026
163 Mengikuti265 Pengikut
Tweet Disematkan
m-ret
m-ret@mretsal·
So basically typing claude runs the standalone binary (the one from claude.ai/install.sh or npm install -g). That binary ships with a custom Bun fork that silently does native string replacement on every API request (it hunts for the cch=00000 billing sentinel and swaps it). If your conversation ever contains that sentinel string (super easy when you’re discussing limits, billing, or just reading the Claude Code source), it mangles the cache key → prompt cache breaks → you pay 10-20× more tokens on every single turn. That’s why you hit the limits so fast. npx @anthropic-ai/claude-code runs the clean npm package on stock Bun/Node → no replacement happens → caching works properly → token usage stays normal (27 % after 2 hours of heavy prompting, as I posted).
m-ret@mretsal

Game changer: started using `$ npx @anthropic-ai/claude-code` to fire up Claude Code in the terminal… and the absurd token usage limits are GONE. Been prompting hard for almost 2 hours and my current session is only at 27%. We are SO back!

English
16
13
135
70.1K
m-ret me-retweet
Rock Solid
Rock Solid@ShitpostRock2·
Bro saw the error in his ways
Rock Solid tweet media
English
130
3.3K
42K
1.2M
m-ret
m-ret@mretsal·
@theo Let's ban npm install for now
English
0
0
2
1.8K
m-ret
m-ret@mretsal·
@Rasmic Can't understand why there are so many people still using FB tho
English
0
0
0
52
Tom Otto
Tom Otto@launch_llama·
Drop your startup below. I read every single one. The best get featured to 45k founders in Launch Llama 👇 #buildinpublic
Tom Otto tweet media
English
158
1
56
4.6K
m-ret
m-ret@mretsal·
Well now it's not even worth it running npm install anymore 😂
English
0
0
0
19
m-ret
m-ret@mretsal·
@james406 Why didn't you run /remote-control and use it from your phone? It's the future but you are using the tools wrong.
English
2
0
4
839
james hawkins
james hawkins@james406·
i spent the entire day keeping my laptop lid open so my AI agents could run brought portable chargers, tethered to my phone for internet, the whole deal finally, when i got home, i opened my laptop to see the work they'd done nothing had happened because Claude was waiting for permission to open the project folder this is the future of work
English
90
31
1.8K
95.7K
m-ret me-retweet
Andrej Karpathy
Andrej Karpathy@karpathy·
This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral x.com/zan2434/status… There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.
Thariq@trq212

x.com/i/article/2052…

English
703
1.5K
14.1K
1.7M
m-ret
m-ret@mretsal·
@burkov People are not searching for it on Google anymore because they are now actually using it...
English
1
0
6
888
BURKOV
BURKOV@burkov·
This is what a useless hype lifecycle looks like.
BURKOV tweet media
English
206
209
4.2K
269.5K
m-ret
m-ret@mretsal·
On the CLI it's actually how you do this. Just ask the main coordinator agent "spin up 20 specialized sub agents to complete the next task". Sometimes it won't load 20 because it's too much. But 20 it's just a number. You can ask it to run the necessary amount of specialized sub agents to achieve the job.
English
1
0
0
16
karthikk vijay
karthikk vijay@dr_kvj·
@mretsal @Hesamation @thegenioo @thsottiaux Oh the CLI mode can do that? But how do u coordinate with all of them in a single command tab? Also, are u talking about spinning up sub agents to work in parallel? Cos thats possible already
English
1
0
0
23
Hamza
Hamza@thegenioo·
I've noticed that hardcore coders prefer using Codex in CLI rather than macOS app What's the reason?
English
153
3
593
115.9K
m-ret
m-ret@mretsal·
@Hesamation I think this is fair. It has slow down because now it has users that are not searching for it anymore, they are using it.
English
0
0
10
409
ℏεsam
ℏεsam@Hesamation·
OpenClaw’s trend is wearing off into non-existence.
ℏεsam tweet media
English
108
22
447
71.8K
m-ret
m-ret@mretsal·
I've been using @unosendco and it's pretty awesome as well.
@levelsio@levelsio

If you wanna switch to @Cloudflare Email Sending today, here's my prompt for you, as always I'm unaffiliated, not paid, not sponsored, but I like it, make sure you remove the space before the .com in the API url I added to avoid it becoming a link in this tweet: # Prompt: Migrate transactional email to Cloudflare Email Service Paste this into Claude Code (or Cursor, or any agent) running inside your project. --- I want to migrate this codebase's outbound email from its current provider (Postmark / SES / Resend / SendGrid / Mailgun / etc.) to Cloudflare Email Service (public beta, launched April 2026). Help me do this carefully. ## Context: what Cloudflare Email Service is A new transactional email API from Cloudflare. Endpoint: ``` POST https://api.cloudflare .com/client/v4/accounts/{ACCOUNT_ID}/email/sending/send Authorization: Bearer {API_TOKEN} Content-Type: application/json ``` Request body: ```json { "to": "user@example.com", // string OR array of strings "from": "no-reply@yourdomain.com", // string OR {"address":"x@y","name":"Display"} "subject": "...", "html": "

...

", // optional "text": "...", // optional (one of html/text required) "cc": ["..."], // optional, array "bcc": ["..."], // optional, array "reply_to": "...", // optional, single string "headers": {"List-Unsubscribe": "<...>"} // optional, e.g. for newsletters } ``` Success response: HTTP 200 + `{"success":true,"result":{"delivered":[],"queued":[],"permanent_bounces":[]}}`. Failure: non-200 OR `success:false` OR non-empty `permanent_bounces`. Always check all three. Pricing: $5/mo Workers Paid plan + 3,000 emails free + $0.35 per 1k after. Roughly 5× cheaper than Postmark. No batch send endpoint — loop single sends. ## Steps you should follow ### 1. Verify prerequisites with me Before writing any code, ask me to confirm: - I have a Cloudflare Workers Paid plan ($5/mo) - I've onboarded my sender domain(s) in Cloudflare dashboard → Email → Email Sending → Onboard Domain (this auto-adds SPF/DKIM/DMARC + cf-bounce MX records) - I have an API token with `email_sending:write` scope (created at dash.cloudflare.com/profile/api-to… → Custom Token) - I have my Cloudflare account ID Don't proceed until you have these. ### 2. Recommend a domain reputation strategy Most apps should split senders across 2-3 subdomains so spam complaints on one don't drag down deliverability on others: - `mail.` or `members.` → transactional (login, receipts, password reset, in-app notifications) - `e.` → cold/recovery (abandoned cart, win-back campaigns) - `newsletter.` → opt-in newsletters with List-Unsubscribe headers Each subdomain needs to be onboarded separately in Cloudflare. Ask me which I want. ### 3. Audit existing email sends Use grep/search to find every place in this codebase that sends email. Look for: - The current provider's SDK class names, API URLs, env/config vars - Generic patterns like `mail()`, SMTP usage, `nodemailer`, etc. Group findings by email type/purpose (e.g. "magic-link login", "payment receipt", "weekly newsletter") rather than by file. Tell me what you found before changing anything. ### 4. Add a single helper function Don't sprinkle Cloudflare API calls across the codebase. Add one helper (provider-specific name like `sendEmailViaCloudflare()`) that: - Defaults `from` from a config var (don't hardcode) - Parses `"Name @domain>"` strings into the API's `{address, name}` object form - Accepts `cc`/`bcc` as either string or array - Accepts a `headers` dict (newsletters need `List-Unsubscribe` + `List-Unsubscribe-Post`) - Returns `bool` (true on success, false on any failure) - On failure, logs/alerts somewhere I can see (Telegram, Sentry, log file — match what the codebase already does) - Sets curl/fetch timeouts (5s connect, 15s total) so a stuck CF API can't hang the request - Treats `permanent_bounces: [...]` non-empty as a soft failure ### 5. Migrate one low-stakes email type first Don't migrate everything at once. Pick the lowest-stakes email type in the audit (something where landing in spam wouldn't lose me money or users — e.g. "internal admin alert", "profile photo rejection") and migrate just that one. Test it end-to-end. Confirm the email actually arrives. Only then propose the next migration. ### 6. Stop me from migrating login email yet If my codebase sends magic-link login or password-reset emails, do not migrate those to Cloudflare yet. Cloudflare Email Service is brand new (~1 month old at writing). Its IP/domain reputation is unproven. Login emails landing in spam = users locked out. Keep those on the current provider until at least 3 months of clean deliverability data on the lower-stakes types. Tell me this explicitly. ### 7. Suggest commit boundaries After each successful migration, suggest a focused git commit with a clear message. Don't bundle unrelated changes. ## Important caveats to surface to me - Beta product. Pricing isn't fully finalized. SLA undefined. Could change. - No batch endpoint. Mass sends (newsletters to 1000+ recipients) need a loop — at ~150ms/send that's ~2.5min per 1000. Fine for crons, bad for sync user-facing flows. - No bounce webhooks yet. Surface failures via the response body's `permanent_bounces` array. - Suppression list auto-managed. Hard bounces, repeated soft bounces, and spam complaints get blocked. Spam-complaint suppressions are hard to remove (anti-abuse). - No per-message logs/dashboard yet. Use the response's `messageId` for tracking if I need it. - List-Unsubscribe headers are passed through verbatim — Gmail's bulk-sender requirement still met, but only if I include them in `headers`. ## Your first action Before writing any code: do step 1 (ask for prerequisites) and step 3 (audit existing sends), then propose the migration order with a brief explanation of the reasoning. Wait for my confirmation before making changes.

English
0
0
0
27
m-ret
m-ret@mretsal·
@Hesamation @naval Yeah but he also said that APIs and UIs are dead so...
English
0
0
4
119
Harushika
Harushika@harushika47·
今日の持ちもの。 18時過ぎでもまだ明るくて、 日が長くなってきたと感じる今日この頃。 アイテムの詳細はALTに。
Harushika tweet mediaHarushika tweet mediaHarushika tweet media
日本語
3
11
311
20.5K
m-ret
m-ret@mretsal·
@evilrabbit_ Is there an online store to buy these pieces?
English
1
0
0
264
Evil Rabbit
Evil Rabbit@evilrabbit_·
I told you, some of these collectibles are in-sa-ne.
Evil Rabbit tweet mediaEvil Rabbit tweet media
English
20
10
421
28.9K
m-ret
m-ret@mretsal·
Americans as soon as they arrive to a beach in Costa Rica
English
0
0
1
176
Omni Driver
Omni Driver@t_sanguinetti·
En algún momento, las pantallas van a quedar para los autos baratos y las marcas premium van a volver a esto.
Omni Driver tweet media
Español
370
1.1K
27.1K
625.5K
m-ret
m-ret@mretsal·
@richkuo7 @kirillk_web3 Yeah you are right. These AI influencers understand half of what they are spreading across social networks.
English
1
0
5
549
Rich Kuo
Rich Kuo@richkuo7·
@kirillk_web3 People who have used Kimi for anything agentic knows this is all false lol
English
10
0
166
10.6K
Kirill
Kirill@kirillk_web3·
> be Kimi > nobody outside China pays attention > everyone paying $200/month for Claude > Kimi already there. 8x cheaper. > drop K2.6 > 300 sub-agents. 4,000 steps simultaneously. > 12 hours continuous execution. zero human oversight. > beats Claude Opus 4.6 on SWE-Bench Pro > open weights. free. > Vercel: "50%+ improvement on our benchmark" > while everyone was paying for closed models > Kimi was quietly becoming the infrastructure > different game.
Kirill@kirillk_web3

x.com/i/article/2046…

English
139
243
4.3K
742K
Ranju
Ranju@whatRanjuSaid·
@Ekaeoq what did u switch to
English
1
0
0
82
Ekaeo
Ekaeo@Ekaeoq·
Can't believe I used to code for a living, wouldn't wish it upon my worst enemy
Ekaeo tweet media
English
13
1
174
6.7K