DEV Community

Shouvik Palit profile picture

Shouvik Palit

Hi, I build unusual tools for developers. Currently: DEV·TV — a TV for the developer internet. 10 channels · GitHub · Hacker News · DEV · Hugging Face · CVEs · Video

I turned all 14 of my GitHub repos into TV channels

I turned all 14 of my GitHub repos into TV channels

1
2 min read

Want to connect with Shouvik Palit?

Create an account to connect with Shouvik Palit. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
I added a LOCAL MODELS channel to my retro dev TV, and Ollama has no API for it

I added a LOCAL MODELS channel to my retro dev TV, and Ollama has no API for it

1
1
3 min read
NVIDIA Just Dropped an Open-Weight Speech Model. I Caught It on My Retro TV 1 Hour Later.

NVIDIA Just Dropped an Open-Weight Speech Model. I Caught It on My Retro TV 1 Hour Later.

1
2 min read
I pointed my Claude skill at 3 famous repos, and it animated their READMEs 🎨

I pointed my Claude skill at 3 famous repos, and it animated their READMEs 🎨

2
3 min read
DEV·TV's second real ad is live, and the next one could be yours 📺

DEV·TV's second real ad is live, and the next one could be yours 📺

3
2
2 min read
🥊 GPT-6.1 Terra vs Kimi K3.1 Pro: DEV·TV Called It 3–1

🥊 GPT-6.1 Terra vs Kimi K3.1 Pro: DEV·TV Called It 3–1

1
2 min read
GPT-6.1 Terra is on DEV·TV

GPT-6.1 Terra is on DEV·TV

2
1 min read
I built a token killer for AI agents. Here's what it didn't kill.

I built a token killer for AI agents. Here's what it didn't kill.

1
4 min read
leantext's first small win: 49 clones in two days

leantext's first small win: 49 clones in two days

1
2 min read
leantext: up to 99% fewer tokens when your coding agent reads the web

leantext: up to 99% fewer tokens when your coding agent reads the web

4 min read
DEV·TV now runs real ads, and the first one is mine

DEV·TV now runs real ads, and the first one is mine

5
2 min read
My coding agent read 92,348 tokens to learn what NumPy is. So I built leantext.

My coding agent read 92,348 tokens to learn what NumPy is. So I built leantext.

1
5 min read
An AI that argues with itself is now on DEV·TV's Spotlight

An AI that argues with itself is now on DEV·TV's Spotlight

1
2 min read
New models every week, so I built a channel that makes them fight

New models every week, so I built a channel that makes them fight

4
3 min read
MiniMax M3.1 Flash just went free on OpenRouter. Here's what it is.

MiniMax M3.1 Flash just went free on OpenRouter. Here's what it is.

2
3 min read
The company that made DEV·TV's first video is now on its Spotlight

The company that made DEV·TV's first video is now on its Spotlight

2
2 min read
A Star Is Vanity. This One Wasn't.

A Star Is Vanity. This One Wasn't.

6
3
3 min read
Spotted on DEV·TV: FLUX 3 Image Klein just landed, and it renders text like a sign painter

Spotted on DEV·TV: FLUX 3 Image Klein just landed, and it renders text like a sign painter

1
2 min read
I built a TV for developers 📺 (13 live channels, no signup)

I built a TV for developers 📺 (13 live channels, no signup)

5
3 min read
Just in: Drex v2.0, a model that decides instead of writing, lands on DevTV

Just in: Drex v2.0, a model that decides instead of writing, lands on DevTV

1
3 min read
DEV·TV won the week on IndieNeed 🏆 (a single HTML file, no backend)

DEV·TV won the week on IndieNeed 🏆 (a single HTML file, no backend)

5
3
3 min read
What would your GitHub look like as a TV news report?

What would your GitHub look like as a TV news report?

7
8
2 min read
Decision models are a new category, and Microsoft just joined it

Decision models are a new category, and Microsoft just joined it

5
3
3 min read
I launched a one-file side project on 5 platforms. Here's what each one actually gave me.

I launched a one-file side project on 5 platforms. Here's what each one actually gave me.

4
9
3 min read
Spotlight: a TV channel for developer projects, featuring what people actually build 📺

Spotlight: a TV channel for developer projects, featuring what people actually build 📺

1
2
2 min read
This just in: StepFun Step 5 Preview showed up on my TV 53 minutes after release

This just in: StepFun Step 5 Preview showed up on my TV 53 minutes after release

1 min read
CiCrew Is Spotlight #2 on DEV·TV 📺

CiCrew Is Spotlight #2 on DEV·TV 📺

7
4
2 min read
Astratide Is Live on DEV·TV 📺

Astratide Is Live on DEV·TV 📺

3
2 min read
DEV-TV Alert !!! New Model

DEV-TV Alert !!! New Model

2
1 min read
Tencent just dropped Hy Image 3.5 Preview. DEV·TV is already showing it. 📺

Tencent just dropped Hy Image 3.5 Preview. DEV·TV is already showing it. 📺

2
1
2 min read
DEV·TV v2: a guide button and an Agent Skills channel 📺

DEV·TV v2: a guide button and an Agent Skills channel 📺

2
5 min read
DEV·TV now has three skins: Graphite, Walnut, and Cream

DEV·TV now has three skins: Graphite, Walnut, and Cream

4
2 min read
Clef-Flash: the 9B model that decides instead of chats (I spotted it on DEV·TV)

Clef-Flash: the 9B model that decides instead of chats (I spotted it on DEV·TV)

4 min read
What If the Developer Internet Had a TV? 📺

What If the Developer Internet Had a TV? 📺

3
2 min read
A New AI Model Just Showed Up on My TV And I Finally Got Why I Built DEV·TV

A New AI Model Just Showed Up on My TV And I Finally Got Why I Built DEV·TV

1
2 min read
There are too many new AI models. So I put them on TV.

There are too many new AI models. So I put them on TV.

1
2 min read
DEV·TV's first Community Spotlight

DEV·TV's first Community Spotlight

2 min read
DEV·TV finished #5 Product of the Day on Product Hunt. Here's what I learned.

DEV·TV finished #5 Product of the Day on Product Hunt. Here's what I learned.

1
3 min read
I Built a TV for the Developer Internet, and Verified Every Claim I Made About It

I Built a TV for the Developer Internet, and Verified Every Claim I Made About It

4 min read
Implementation Scout: Making AI Prove Its Coding Advice Instead of Just Sounding Confident

Implementation Scout: Making AI Prove Its Coding Advice Instead of Just Sounding Confident

4 min read
I Reduced AI Response Tokens by 44% Without Changing the Model

I Reduced AI Response Tokens by 44% Without Changing the Model

2 min read
Sir Shortoken: Bullet Mode, Local Expansion, and What Actually Held Up

Sir Shortoken: Bullet Mode, Local Expansion, and What Actually Held Up

5 min read
Sir Shortoken: Disciplined AI Output for Every LLM

Sir Shortoken: Disciplined AI Output for Every LLM

5 min read
I built a runtime that stops AI agents from over-engineering everything

I built a runtime that stops AI agents from over-engineering everything

2 min read
Ship Happens: How I Made a 3B Local Model Trustworthy for Kubernetes (By Never Trusting It)

Ship Happens: How I Made a 3B Local Model Trustworthy for Kubernetes (By Never Trusting It)

5 min read
I tracked every GitHub traffic spike for my open source LLM proxy for 7 weeks. Then I did the exact same thing again, and it worked again.

I tracked every GitHub traffic spike for my open source LLM proxy for 7 weeks. Then I did the exact same thing again, and it worked again.

5 min read
Your Session History Is Bleeding Tokens Every Time You Paste

Your Session History Is Bleeding Tokens Every Time You Paste

2 min read
Stop explaining yourself to Claude

Stop explaining yourself to Claude

3 min read
Escalate the Model, Not the Conversation

Escalate the Model, Not the Conversation

2 min read
How I Cut Agent Token Usage by 89% Without Touching the Agent

How I Cut Agent Token Usage by 89% Without Touching the Agent

4 min read
I Added a Live Dashboard to My LLM Proxy. Zero Instrumentation. Just a URL Change.

I Added a Live Dashboard to My LLM Proxy. Zero Instrumentation. Just a URL Change.

2
3 min read
I Added a /recovery Endpoint to My LLM Proxy So Agents Never Lose Progress Mid-Task

I Added a /recovery Endpoint to My LLM Proxy So Agents Never Lose Progress Mid-Task

3 min read
I Tested Privacy-Aware Routing with 4 AI Agents: What Actually Stayed Local

I Tested Privacy-Aware Routing with 4 AI Agents: What Actually Stayed Local

4 min read
How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out

How I built a Go proxy that keeps your LLM conversation alive when cloud quota runs out

1
1
2 min read
loading...