ibo Turnam

🎶 Musikproduzent 🎸

[ibo Turnam @Turnam_ibo]

@yurtdisituyo 6 Rue Perrière74000 Annecy, Frankreich

[LUKE @LukeFurryjo]

This damn beat is hitting viral

[Para Mühendisi @paramuhendisim]

MIT öğrencilerine özel hazırlanan Servet İnşa Etme dersi. Türkçe altyazılı

İzledikten sonra bana teşekkür edeceksiniz.

[Josh Barzon @JoshuaBarzon]

Ethnic Composition of the Middle East

[Özcan Çelik @ozcancelik]

Harfiyen v0.2.0
Türkçe'den Türkçeye düblaj: Yapay ses baştan okuyor, dayı artık anlaşılıyor.(ema-lightning, antalia-mini)
Bul ve değiştir: Yanlış kelimeyi tek seferde düzelt
SRT/VTT içe aktarma: Altyazını aç, stillendir, videoya yaz
https://t.co/zPBweU1v9o
https://t.co/RQHRYHFhQw

[Bi Bak! @haberebibak]

İstanbul'daki 2. ve 3. Levent'in akıbeti paylaşıldı:

🔺 1947'deki konut krizini çözmek için Levent arazisinde 4 etaplı konut projesi başlatıldı.
🔺 Proje; bahçeli evleri, parkları ve çarşısıyla planlandı.
🔺 1980'lerde Büyükdere Caddesi'nin iş merkezine dönüşmesiyle bahçeli evler ofis ve restoranlara dönüştü.
🔺 Metro duraklarında Levent ve 4. Levent isimleri kalırken, 2. ve 3. Levent imar değişiklikleriyle bölgenin içine karıştı.

[Köksal ÖZTÜRK @06koksal71]

Özdemir Erdoğan ben masonluktan istifa ettikden sonra 🤔

[Gazetory @gazetory]

ABD'de 61 yaşındaki kadın sporcu, 5 saat boyunca plank pozisyonunda kalarak dünya rekoru kırdı.

[Milos @milos_gis]

50 years of 4103 earthquakes in Türkiye🇹🇷, path-traced in forge3d

[Delta Metrik @deltametrik]

Yüz binlerce dolar maaş alan Claude ekibi, doğru şekilde nasıl prompt yazılır öküze anlatır gibi anlatmış.

Türkçe altyazılı.

[Md. Sagor Hosen @sagorhosen93]

50 legendary websites that feel like the internet’s hidden toolbox 🧰

1. https://t.co/B0gUX2C3Ea — free research papers
2. https://t.co/S1tVgrTMEB — papers when unpaywall misses
3. https://t.co/tfV1Z4sYmT — borrow books
4. https://t.co/p3KVUr5JIZ — 70k+ free books
5. https://t.co/5CRdidUse1 — audit university courses free
6. https://t.co/rPqpyaSSJB — step-by-step math
7. https://t.co/7MmIgKnbYc — background removal
8. https://t.co/PA6BSFTKe6 — object removal
9. https://t.co/39fUXgNOEr — quick file tools
10. https://t.co/NdxkDMRoHK — PDF merge/split
11. https://t.co/aXc8FT7Ctn — free Photoshop alternative
12. https://t.co/DtLtoUz97w — image compression
13. https://t.co/Ziv6JnBfD2 — fast diagrams
14. https://t.co/ygtHPvdfyH — beautiful code screenshots
15. https://t.co/CHwxWaVmWP — test regex
16. https://t.co/bxaR0Dm2Nj — clean JSON
17. https://t.co/SHtzu3FrVn — terminal commands explained
18. https://t.co/J3OBc96JR7 — software alternatives
19. https://t.co/abCPAqkr6b — breach check
20. https://t.co/z2757aFybL — temp email
21. https://t.co/AvoNdK4EIo — self-destruct notes
22. https://t.co/OgikB4oZWs — live global radio
23. https://t.co/SPIehUmRBm — focus sound
24. https://t.co/Qfa6H1ASKB — custom ambient
25. https://t.co/IDEiIv2KpA — where to stream
26. https://t.co/QdRNsZiBLa — digital library
27. https://t.co/fKz1u9ShpI — old web pages
28. https://t.co/2HBRZgMXm0 — site traffic
29. downtimerobot — uptime check
30. https://t.co/zn1WLkedUq — speed test
31. https://t.co/utrglbONIT — compress images
32. https://t.co/GzNjwtAIv6 — file conversion
33. https://t.co/l2scTHupRU — compare text
34. https://t.co/3qomLdbrxc — disposable inbox
35. https://t.co/iR0EfKETEB — JS obfuscate
36. https://t.co/YPX6emcR93 — typing practice
37. https://t.co/Oii41P0Ng5 — typing test
38. https://t.co/sKmKwI38Nx — spaced repetition
39. https://t.co/cQm1jQdcIR — all-in-one notes
40. obsidian.md — local knowledge base
41. https://t.co/GEft7vriBE — bookmark manager
42. https://t.co/chHqpp6JZv — task list
43. https://t.co/1YiVMZpWTp — boards
44. https://t.co/TQhgtekyYV — whiteboard
45. https://t.co/Vn1jbW7sA5 — design
46. https://t.co/saGDxVtSn9 — quick graphics
47. https://t.co/7MmIgKnbYc — again because it's that good
48. yt-dlp — video download (open source)
49. https://t.co/2PyQTJda5a — video compress
50. https://t.co/qgioutyDPx — local file transfer

Save this. You’ll definitely need some of these later. 🔖
Follow @sagorhosen93 for more useful websites, AI tools & tech resources.

[rody @0x_rody]

this is pure f*cking treasure

a team of researchers found how to orchestrate Claude Opus 5.5 and Jev together, and it completely breaks the agent scaffolding wall

most developers try to make an agent reliable by routing every decision back through the model. you burn tokens on choices that have an exact rule and freeze your routing logic into a prompt that drifts within 5 edits

this architecture eliminates human-written routing prompts and splits the cognitive stack:

search director: Claude Opus 5.5 plans the work, querying a persistent decision graph where routing and scoring reduce to single typed calls

typed router: Jev answers every fork in code, returning an option with a probability instead of prose

zero context bleeding: a routed fork never enters the chat context, so a thousand decisions cost the same context as zero

evaluator isolation: candidate code never touches the scoring process, stopping reward hacking and test leakage cold

handoff contract: every step passes task, inputs, done-condition and confidence as a file, so a crashed session loses nothing

the metrics outclass single-context agent loops:

7x lower model spend than running the same loop through one context window
0 tokens generated on routed decisions
sub-500ms on forks that used to cost a full frontier round trip
0% reward hacks: candidate-controlled metric tampering eliminated

Opus directs the plan. Jev picks the branch

you stop writing rigid routing prompts. you let the type system own the decision loop

I'll leave some ready-to-copy Jev builds in the article below ↓ ↓

[Adnan Sharif Lihaz @lihazadn_Ai]

19 year old Japanese student built a trading bot with Claude Code in 2 days.

Used his iPad as a second monitor.

First night: $6,732 profit.
Starting capital: $68.

Total profit so far: $750,000.

[ 𝐍𝐨𝐭𝐞: 𝐅𝐨𝐥𝐥𝐨𝐰 𝐌𝐞 @lihazadn_Ai 𝐅𝐨𝐫 𝐢𝐧𝐬𝐭𝐚𝐧𝐭𝐥𝐲 𝐚𝐮𝐭𝐨 𝐃𝐌]

Here's how it works👇

The bot scans over 50 markets simultaneously.

Syncs live BTC data from Binance every second.

Spots price errors before humans even notice.

The edge is pure speed + pattern recognition.

While traders stare at charts trying to predict the next move, his bot is already executing on mispricing across dozens of markets.

No guessing.
No emotions.
No hesitation.

Just Claude Code logic finding gaps that close in seconds.

He built the entire system in 48 hours:

— Claude Code handles the trading logic
— Binance API feeds real-time BTC data
— iPad displays multi-market monitoring
— Executes trades when arbitrage windows open

The system runs 24/7.

Every price dislocation = profit opportunity.

Most people are still trading manually, refreshing charts, second-guessing entries.

Meanwhile this 19 year old engineering student turned $68 into $750K by letting Claude Code do what humans can't: process 50 markets instantly and execute without fear.

Why are people still trading manually?

I'm giving away the exact Claude Code setup for free.

24 hours only.

To get it:
1️⃣ Comment " Setup "
2️⃣ Like and Repost
3️⃣ Follow @lihazadn_Ai (so I can send it via DM)

I'll DM you the complete setup.

[Beaver @Beaver_0x]

whoever built this realized we’ve been using our smartest AI for the dumbest possible jobs

your $25-$250/mo frontier model is researching, writing code, planning…

and then you’re paying the same brain to decide YES / NO.

Jev flips that.

it’s a tiny decision model that sits in front of the expensive stuff and handles the boring forks:

-> which agent goes next?
-> is this worth researching?
-> reply or ignore?
-> publish, wait or escalate?
-> BUY / SELL / HOLD?
-> click this or keep looking?

then I saw the numbers people are reporting and the whole architecture started making a lot more sense.

~2,000 papers classified for around $0.05
~800 emails sorted for around $0.028

browser-agent loops demonstrated around 6 seconds for ~$0.0029

and at the quoted pricing, roughly 20,000 ~2K-token decisions comes out around $0.62.

that’s not because Jev became smarter than Claude.

it’s because nobody asked it to be Claude.

the setup is stupidly simple:

-> big LLM gets the hard thinking, research and writing
-> Jev gets the thousands of tiny decisions between those steps
-> code actually clicks, saves, sends and executes

and suddenly you start noticing these little decisions everywhere.

> your inbox.
> X feed.
> support queue.
> meetings.
> leads.
> video clips.
> browser agents.
> even paper-trading loops.

that’s the part I think most agent builders are missing.

the expensive model doesn’t need to touch every step just because it’s capable of touching every step.

> let Claude think.
> let Jev decide what deserves Claude.
> let code do the actual work.

I broke down 12 places you can wire this into an agent today + the exact router setup in the article below

[kiosa @thegreatest_sv]

this JEV is certified f*cking diamond

every agent you ship burns frontier tokens on questions that were never writing jobs

is this spam? which worker goes next? is the draft good enough to show a human?

those are decisions. Jev is built for that half of the loop

you send state plus a typed question. it returns a choice, a score, or yes/no with confidence. no chat. no second opinion

the public demos, not our lab:

> ~1,000 papers classified for about $0.08, median around 256ms
> ~500 emails in one inbox pass for about 3.5¢
> a flight search loop in about 7 seconds for about $0.0039
> a huge Claude session compacted from ~1M tokens down to ~86k in about a second

the whole trick is the split

if it creates, the LLM writes
if it picks, scores, or gates, Jev decides
if it does the thing, code does it

pricing people quote: about $0.042 per million tokens in. output free. 10,000 decisions is about $0.42

a local router makes it obvious. goal plus what's already done. Jev picks research, write, or review. confidence under 0.85 goes to a human. the job lands as JSON in a folder. the writer never wakes up for a yes/no

and the loop refuses to publish on its own

drafts go to review. you hit post. Jev never sends the tweet

one model writes. a cheaper one decides. nothing irreversible ships until a human says yes.

[kiosa @thegreatest_sv]

honestly this should be f*cking illegal

your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago.

Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs.

3 repos already built on it:

-> jev-trader: one AI trade decision every single block, on a live MON-USDC market
https://t.co/oTz9vrh5bl

-> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading
https://t.co/ToQAwqijxb

-> AIStock: "one person can become their own super-analyst"
https://t.co/0xOXAb7MBi

$0.042 per million input tokens. output is free.

that's thousands of decisions for the price of one LLM call.

the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first.

> let the big model do the research.
> let Jev pull the trigger.
> let code set the stop.

bookmark this before your bot is the slow one in the room.

[marfin @marfinxx]

this is pure f*cking treasure

A Stanford research group found how to orchestrate Claude Opus 5.5 and GPT-6 Astra together, and it completely breaks the resampling wall

most developers think test-time compute means running 32 blind retries on one model. you burn API tokens repeating the same 2-3 error clusters in loops

Stanford's paper (arXiv:2608.05643) splits the compute between two different brains:

> breadth search: GPT-6 Astra runs high-entropy exploration (T=0.8) to discover divergent solution paths
> step audit: Claude Opus 5.5 scans each step at T=0.0 and catches the exact logic fallacy
> local surgery: Opus rewrites only the broken step instead of dumping the whole reasoning chain
> verifier-free consensus: majority voting locks the proof without relying on drift-prone PRMs

the benchmark metrics outclass standard Best-of-N sampling:

> 91.2% recovery rate on detected reasoning flaws
> under 1.8% regressions on correct branches
> MATH500 jumps from 29.6% to 58.0% (+28.4% absolute gain)
> AMC-2023 improves by +7.5% with zero reward models

Astra explores the maze. Opus repairs the logic

you stop burning tokens on blind retries. you run verified reasoning depth

[savip. @savipww]

OKAY THIS IS GETTING F*CKING INSANE, MY CRAWLER WRAPS SCAM COINS IN SILK WHILE I SLEEP AND JEV + MY GROK BOTS TOOK MY $100 TO $23,879

my crawler post hit 1.2M views on night 3, then half my timeline copied it

so last night i taught mine three new moves

the crawler = a bot that combs crypto Twitter for me all night

Jev = an AI with two answers, yes and no, quicker than a blink, cheaper than a gumball

spider reads, Jev rules, Grok bots click buy and sell

the new moves:
→ radar, circles the top wallets, pings big sellers
→ cocoon, wraps a fake coin in silk, drops it
→ audit, zigzags over my balance, checks every fill

the coin:
HOOKI, 3 hours old, $460K at 10pm, Jev gave it a yes

overnight:
→ 10:20pm first entry came too early, -$271
→ 11:15pm it crashed to $150K, holders down 67%
→ 11:20pm buyers came back, Jev said buy at $366K
→ 11:55pm sold at $718K, +$2,008
→ 1:45am night's bottom $279K, Jev said go, sold $558K, +$2,188
→ 6:15am Jev said buy at $224K, out on the 6:50am close, +$750
→ two smaller wins, +$1,910

anyone who bought HOOKI at 10pm and held woke up 40% poorer

my bots finished up 35.6% trading that exact chart

honestly i'd pay for the cocoon alone, the coins i skip save me more than the ones i buy

night 1 $2,197, night 2 $4,962, night 3 $12,161, night 4 $17,608, night 5 $23,879

at 0:11 the spider wraps a scam coin and drops it

bookmark it, night 6 is tonight

all of it is below ↓ free

send this to whoever copied the crawler first

be honest, who picks better coins at 3am, you or a spider?

[Paone @paonx_eth]

I GAVE JEV A CRAWLER + ONE GPT AGENT AND ASKED WHERE THE ONLINE MONEY IS RIGHT NOW

it read 5,137 open jobs and found 3 niches where clients pay and almost nobody bids

everyone asks chatgpt for side hustle ideas

everyone gets the same 10 answers

so i made it read what clients are actually paying for this week

a crawler is a bot that reads the internet for you

jev is the ai that answers every question with a number, under a second, under a cent

gpt is the expensive brain, it only gets called when jev says a niche is worth it

the crawler reads, jev decides, gpt researches

honestly gpt alone just guesses, jev is what turns 5,137 jobs into 3 answers

what the three of them did:

-> crawler read all 5,137 open jobs on freelancer, budgets, skills, how many people already bid

-> jev checked every one: real job? doable online by one person? 684 got cut

-> gpt named 30 niches from 600 of them, jev sorted all 4,453 into those niches

-> jev looked at each niche's numbers and sent only 12 to gpt

-> gpt researched those 12 on the open web: other platforms, real prices, how crowded it is

-> 3 came back with real demand and fewer bids than the typical job (14):

01 chrome extension · 85 jobs this week · median $545 · 11 bids each · ~$4,671/mo

02 tiktok shop setup · 91 jobs this week · median $232 · 6.5 bids each · ~$1,984/mo

03 notion setup · 95 jobs this week · median $181 · 3 bids each · ~$1,551/mo

potential = your fair share of this week's jobs (budget ÷ (bids + 1)), max 2 jobs a week

not every pick held up, excel dashboards looked great on freelancer but gpt found it crowded everywhere else

jev made 9,617 calls for $0.13, gpt on every job would have cost ~$58.66, the whole run cost $6.53

i wrote up why the cheap brain decides and the expensive one only gets called when it's worth it, it's below ↓ costs nothing

bookmark this, empty niches don't stay empty

show this to the one friend who keeps asking chatgpt for side hustle ideas

should i run it on upwork next, or is chrome extension the one?

[kiosa @thegreatest_sv]

whoever built this realized we’ve been using our smartest AI for the dumbest possible jobs

your $20-$200/mo frontier model is researching, writing code, planning…

and then you’re paying the same brain to decide YES / NO.

Jev flips that.

it’s a tiny decision model that sits in front of the expensive stuff and handles the boring forks:

-> which agent goes next?
-> is this worth researching?
-> reply or ignore?
-> publish, wait or escalate?
-> BUY / SELL / HOLD?
-> click this or keep looking?

then I saw the numbers people are reporting and the whole architecture started making a lot more sense.

~1,000 papers classified for around $0.08
~500 emails sorted for around $0.035

browser-agent loops demonstrated around 7 seconds for ~$0.0039

and at the quoted pricing, roughly 10,000 ~1K-token decisions comes out around $0.42.

that’s not because Jev became smarter than Claude.

it’s because nobody asked it to be Claude.

the setup is stupidly simple:

-> big LLM gets the hard thinking, research and writing
-> Jev gets the thousands of tiny decisions between those steps
-> code actually clicks, saves, sends and executes

and suddenly you start noticing these little decisions everywhere.

> your inbox.
> X feed.
> support queue.
> meetings.
> leads.
> video clips.
> browser agents.
> even paper-trading loops.

that’s the part I think most agent builders are missing.

the expensive model doesn’t need to touch every step just because it’s capable of touching every step.

> let Claude think.
> let Jev decide what deserves Claude.
> let code do the actual work.

I broke down 12 places you can wire this into an agent today + the exact router setup in the article below