jasim_ab Profile Banner
Jasim Profile
Jasim

@jasim_ab

Followers
2K
Following
4K
Media
227
Statuses
8K

"Our ambition was to develop the ultimate abstraction mechanism that subsumed all other abstraction mechanisms"

Joined August 2009
Don't wanna be here? Send us removal request.
@jasim_ab
Jasim
5 days
RT @dhh: What a cool behind-the-scenes look at how @Beelinkofficial builds their mini PCs. Didn't know they did so much pre-shipping testin….
0
23
0
@jasim_ab
Jasim
1 month
"what helps the human helps the AI" is a great articulation!. But since the LLM brain lacks our personal context, we need to make explicit things that would've been implicit in human to human communication. Thus the need for examples and do's and don'ts and similar accroutments.
@AtharvaRaykar
atharva
1 month
The endorsement from @simonw has been hugely validating <3. I've been messing with a bunch of workflows for a while, and this rule of thumb has consistently worked so far: "what helps the human helps the AI"
Tweet media one
0
0
3
@jasim_ab
Jasim
3 months
I tried Cursor, I tried Windmill. I turned on agentic mode and turned off my brain. It took me to interesting, exotic places, but not ones I knew the way back from.
@tom_doerr
Tom Dörr
3 months
I wanted to add a 'Login with Github' option to my website. Didn't work right away and decided that I had to break my rule and just push through. 10+ hours later all my LLM calls are now mocked, half my website features seem to be missing and my login still isn't working.
1
0
5
@jasim_ab
Jasim
3 months
RT @ID_AA_Carmack: @rubyrangerr I think you are misunderstanding what this tech demo actually is, but I will engage with what I think your….
0
1K
0
@jasim_ab
Jasim
4 months
RT @paulgauthier: I added some docs that describe my typical aider workflow: using /ask mode to discuss and plan and then saying "/code go….
0
18
0
@jasim_ab
Jasim
4 months
Tally
Tweet media one
@usgraphics
U.S. Graphics Company
4 months
We need a counter-culture design movement that appreciates products that are difficult to use initially, but tremendously fast, easy, accurate, explicit and efficient after topping the learning curve. Ease-of-use is oversold. It's making everything suboptimal and slow.
0
0
0
@jasim_ab
Jasim
5 months
RT @hytradboi: Other kinds of talks. Someone start CheckIfItActuallyWorksCon. I'll help.
0
2
0
@jasim_ab
Jasim
6 months
RT @ShekharGurav: Introducing Xyne (@xyneAI) : AI-first Search & Answer Engine for work. OSS alternative to Glean, Gemini, MS Copilot. ⭕ O….
0
32
0
@jasim_ab
Jasim
7 months
RT @PineDigitalCo: Loom Alternative: There was a thread here on X today about this topic, and it was timely, as I had just canceled my Loom….
0
4
0
@jasim_ab
Jasim
8 months
RT @RealGeneKim: - "as developers, we thought that we might be safe, unlike those doctors and surgeons and plumbers. Instead, we're the fi….
0
7
0
@jasim_ab
Jasim
8 months
I've been on Claude for a while now, monthly renewal is up and was wondering what else, apart from ChatGPT, is out there. Different subscriptions for Chat and IDE is far too expensive. And in the last two weeks Claude has had severe capacity limitations.
1
0
1
@jasim_ab
Jasim
8 months
RT @satnam6502: I made a starter pack of some people I follow on Bluesky from the world of computing, mainly programming languages, systems….
0
1
0
@jasim_ab
Jasim
8 months
RT @tarstarr: I wrote a long essay on why most of the low-code-no-code tool builders haven't made it out of the teenage slumps -- Airtable….
0
41
0
@jasim_ab
Jasim
9 months
RT @ShriramKMurthi: I was pushed by @neeldhara to turn this into a proper blog post. I don't know if what I wrote is "proper", but it's a b….
0
9
0
@jasim_ab
Jasim
9 months
RT @stevekrouse: .@CerebrasSystems is fast enough for sliders
0
3
0
@jasim_ab
Jasim
10 months
RT @andrewlamb1111: @CMUDB @ApacheDataFusio Thank you @andy_pavlo and @CMUDB for the opportunity to blather away about @ApacheDataFusio at….
0
2
0
@jasim_ab
Jasim
10 months
RT @Sirupsen:
Tweet media one
0
11
0
@jasim_ab
Jasim
10 months
RT @vipulved: There's a good argument Llama will be the default pre-trained model given Meta's compute footprint, access to data, research….
0
5
0
@jasim_ab
Jasim
10 months
RT @satnam6502: I'm giving a general lecture about the architecture of @GroqInc's LPU language processing chips, explaining how they are pr….
0
19
0
@jasim_ab
Jasim
11 months
RT @tonofcrates: We called this "plan overlap" when the code implementing two different subtasks is interleaved. The data supported the int….
0
3
0