MMN

[SenSouk @SenSoukApp]

Un coin pour travailler à la maison ?
Table ordinateur pliable : 3 500 FCFA aux Almadies.
Téléchargez SenSouk (Android/iPhone) pour contacter le vendeur.
https://t.co/U1RTANp9Yo

[SenSouk @SenSoukApp]

Vous vendez ou cherchez un article à Dakar ?

Suivez @SenSoukApp pour nos sélections d’annonces locales et des conseils pour mieux présenter vos produits.

Avec SenSouk, adoptez les bons réflexes pour mieux vendre et saisir de nouvelles opportunités d’achat.

[SenSouk @SenSoukApp]

500 téléchargements, 218 comptes, 115 annonces 🇸🇳
Le petit marché SenSouk grandit 💙
Pas encore installé ? https://t.co/1Rq9BdlaH0
Déjà sur l’app ? Un coup de cœur, un truc qui coince ? Dites-nous 👇
Des nouveautés arrivent. La suite s’écrit avec vous !

[SenSouk @SenSoukApp]

134 comptes sur SenSouk… on va devoir rajouter des chaises 😄
29 nouveaux en 7 jours (+93 % vs les 7 jours précédents) !
Vous avez installé l’app ? Un coup de cœur ❤️ ? Un truc qui vous a fait lever un sourcil 🤨 ?
Dites-nous tout 👇

[SenSouk @SenSoukApp]

🇸🇳 Achetez et vendez près de chez vous avec SenSouk ! Découvrez les annonces, publiez vos articles et échangez directement avec les vendeurs et acheteurs. Téléchargez gratuitement SenSouk sur Google Play.

[SenSouk @SenSoukApp]

🇸🇳 Achetez et vendez près de chez vous avec SenSouk ! Découvrez les annonces, publiez vos articles et échangez directement avec les vendeurs et acheteurs. Téléchargez gratuitement SenSouk sur l’App Store🇸🇳 Achetez et vendez près de chez vous avec SenSouk ! Découvrez les annonces, publiez vos articles et échangez directement avec les vendeurs et acheteurs. Téléchargez gratuitement SenSouk sur l’App Store.

[MMN @___MMN__]

@Chouchouful Assasin

[SenSouk @SenSoukApp]

SenSouk est lancé 🇸🇳

Acheter, vendre, échanger près de chez soi devient plus simple.

Recherchez un produit, comparez les annonces, contactez directement le vendeur.

Et pour publier ? Ajoutez vos photos, l’IA prépare un brouillon, vous vérifiez puis vous publiez.

Disponible sur Android et iPhone.
https://t.co/nglF49l2Vb

#SenSouk #Sénégal #Marketplace #TechAfrica

[Jules Youm 🇸🇳 @jules_youm]

Building Financial DataHub with Codex + GPT-5.6: a personal finance hub that reconciles Wallet, bank statements, SMS, emails and iPhone notifications. What I value most is how technically sharp the model is essential when financial correctness is non-negotiable. #SwitchToCodex

[SenSouk @SenSoukApp]

SenSouk est maintenant disponible sur l’App Store !
Achetez, vendez et trouvez les bonnes affaires près de chez vous, partout au Sénégal.
Téléchargez l’app sur iPhone :
https://t.co/ZffzcAwp46
Android arrive dans 2 semaines.
#SenSouk #Sénégal

[SenSouk @SenSoukApp]

⌛️⏳⌛️⏳

[SenSouk @SenSoukApp]

https://t.co/7mziPbt6ig

[Peter Gostev (in SF @ DevDay) @petergostev]

My view of: Fable 5 vs GPT-5.6-Sol. They are not easy models to compare, these are my vibes - take them as you will.

My overall feel is that Fable is a 'wise owl' who is very thoughtful and very well spoken, GPT-5.6-Sol is like a rottweiler who will grab the problem by the throat and not let go until it is done.

In other words, Fable, is a fundamentally smarter model - even at low reasoning it can be very insightful and writes in a clear compelling way. GPT-5.6-Sol on the other hand is extremely diligent, I can give it a list of 8 things to do and you will be sure that they will be done.

Fable feels more arrogant to me, I was both to get it to build a new benchmark for me - 5.6 worked between 6 hours and 2 days (I tried several times) and it came up with very thoroughly tested, working benchmark. Fable came back within 40 minutes (twice) and the benchmark sounded smart, but was ultimately was 'vibe' based slop and since it was Fable's vibes that was doing the judging, it decided that it was good to go (it kept giving Fable 100% score btw).

Some thoughts by category:

UI & App building: Fable will still craft a better UI from scratch, the flow of the app would probably be a bit nicer. But I find that Fable often misses quite key things, which GPT-5.6-Sol doesn't. GPT's Frontend skills are big jump vs previous GPT models, but still not as great overall.

Writing: Fable is better hands down, Sol feels quite difficult to align to what I want to say or explain things to me simply. Though I think the 'Pro' model writes clearer.

Robustness & Reliability: This is where I think GPT-5.6-Sol wins for me hands down. Fable seems to do things of high quality, but I can never relax with it, it always misses something. With 5.6 this just almost never happens.

Other things where I liked GPT-5.6-Sol, but can't compare to Fable directly.
- Video editing is actually working now, it is not completely perfect, but with the right skill/guidance you can just give it 1h footage and it can give you a 5 min highlight clip no problem
- Computer use - getting really rather good, very usable
- Sub agents - it is very fluent at managing sub-agents and speaking to different threads, can help with some new workflows
- Adhering to existing code patterns - I love this, even without asking it would implement something in a way that aligns with you app - major problem for slop generation
- Research - I think it is getting quite a bit better, it still has some bad patterns (e.g being too tactical), but it feels like it is more steerable to be a good researcher
- Multi-day runs - the /goal feature is pretty insane with 5.6-Sol, you can run it for days if you wanted to and it does work. Useful to have another thread or /side to check up on it, but I have some great results with it
- Token efficiency - it is so much more token efficient and faster than 5.5, in reality it is now much faster than Fable too

On the downside, you can feel that Fable is naturally smarter, and I did have some baffling moments with 5.6 when I was getting it to make a fairly simple change in 8 turns - it seemed to get stuck in a dumb stream that was hard to get out of. So it is not AGI, don't get too carried away by the hype.

I have some phenomenal examples that I'm honestly blown away by that I'll share, but as a side anecdote, I have a kind of 'swear meter' which counts how often I'm rude to Codex. In GPT-5.5 era, the % was at around 4-5%, it dropped to 1-2% when I was testing GPT-5.6-Sol and it shot up to 7% when I went back to 5.5 - it was so shocking to go back to 5.5 and experience how much worse it was.

So is GPT-5.6-Sol better than Fable? On pure intelligence - no. But man, I missed it when I just wanted to get sh*t done. It is insanely capable workhorse that you can give any task to and just expect it to be done. No lectures or 'you are absolutely rightisms', nothing is beneath it, if it takes 2 days to do some dirty work, it will do it.

It feels like the first time in a while when we have quite different types of frontier intelligences that benchmark sort of similarly, but feel very different. If you can, you would be probably better off using both and iteratively finding what you'd use Fable or GPT-5.6-Sol for. Perhaps, something like - an architectural discussion with Fable, implementation with 5.6 and docs & comms with Fable.

[SenSouk @SenSoukApp]

SenSouk arrive en beta au Sénégal.

Achetez, vendez et échangez près de chez vous depuis votre téléphone : annonces, messagerie, profils vendeurs.

Rejoignez les premiers testeurs iOS et Android :
https://t.co/JiyqP7ePbR

[OpenAI Developers @OpenAIDevs]

https://t.co/XlZc6miEid

[Luke The Dev @iamlukethedev]

https://t.co/4bod7AFXo4

[MMN @___MMN__]

@iamlukethedev Flow! This is dope

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[Jules Youm 🇸🇳 @jules_youm]

Nous passons à l’échelle nos activités de coaching et recherchons plusieurs coachs expérimentés dans les domaines suivants :

- Cloud AWS
- DevOps
- Kubernetes
- IA
- Data

L’objectif : accompagner nos apprenants sur des parcours de formation orientés pratique (labs, projets, cas réels), ainsi que sur la préparation aux certifications AWS et Kubernetes.

Profil recherché :

- Solide expérience hands-on en AWS et/ou DevOps
- Certifications AWS appréciées (minimum AWS Solutions Architect Associate)
- Capacité à coacher, expliquer et accompagner dans la pratique
- Très bonne pédagogie et communication
- Expérience dans la création de contenus pédagogiques
- À l’aise avec les formats de coaching en soirée et le week-end

Modalités :

- Freelance / temps partiel
- Coaching, workshops, accompagnement projets
- Apprenants francophones (Afrique & international)

Intéressé(e) ou envie de recommander quelqu’un ?

Postulez directement sur LCF Talents :

- Coach Expert(e) Cloud AWS : https://t.co/B7WE1K9Xd6
- Coach Expert(e) DevOps : https://t.co/kXqxVVwIRT

Pour la partie DevOps, vous pouvez aussi m’écrire directement en DM.

[Jules Youm 🇸🇳 @jules_youm]

This is exactly why personal AI infra should stay model-agnostic.

I still use Claude Code.
But my OpenClaw has been running on OpenAI models for the past 2 months, and I’m very happy with that setup.

Your AI infra should survive vendor policy changes.